| 1 |
deepseek/deepseek-v4-pro-0813
baseten
|
98.56% |
1221 ms |
139 tok/s
2 samples, warming |
2773 with TTFT |
More
- Provider availability
- 98.56% (277 samples)
- Within deadline
- 42.86%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7887 ms
- Failure owner
- provider: 4
- Errors
- empty_output: 3, fusion_validation_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:08:20.000Z
|
| 2 |
mistralai/mistral-medium-3-5
mistral
|
100.00% |
1290 ms |
Not measured
0 samples, warming |
1111 with TTFT |
More
- Provider availability
- 100.00% (11 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3966 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:06:58.000Z
|
| 3 |
deepseek/deepseek-v4-flash-0731
relace
|
100.00% |
1487 ms |
Not measured
0 samples, warming |
1515 with TTFT |
More
- Provider availability
- 100.00% (15 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4466 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:12:44.000Z
|
| 4 |
prism-ml/ternary-bonsai-27b
together
|
100.00% |
1549 ms |
Not measured
0 samples, warming |
453 with TTFT |
More
- Provider availability
- 100.00% (45 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2830 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:22:36.457Z
|
| 5 |
deepseek/deepseek-v4-flash-0731
confidential-ai
|
100.00% |
1619 ms |
160 tok/s
1 samples, warming |
2020 with TTFT |
More
- Provider availability
- 100.00% (20 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4005 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:30:51.000Z
|
| 6 |
reka/reka-edge-2603
reka
|
100.00% |
1653 ms |
Not measured
0 samples, warming |
2222 with TTFT |
More
- Provider availability
- 100.00% (22 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3557 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:13:39.000Z
|
| 7 |
inception/mercury-2
inception
|
100.00% |
1685 ms |
141 tok/s
1 samples, warming |
2323 with TTFT |
More
- Provider availability
- 100.00% (23 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3504 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:46:40.000Z
|
| 8 |
google/gemini-2.5-flash
google-ai-studio
|
100.00% |
1707 ms |
Not measured
0 samples, warming |
1304 with TTFT |
More
- Provider availability
- 100.00% (130 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3062 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:32:26.000Z
|
| 9 |
deepseek/deepseek-v4-flash
deepseek
|
100.00% |
1805 ms |
119 tok/s
1 samples, warming |
959 with TTFT |
More
- Provider availability
- 100.00% (95 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3515 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:36:54.000Z
|
| 10 |
upstage/solar-pro4
upstage
|
100.00% |
1902 ms |
23 tok/s
1 samples, warming |
1313 with TTFT |
More
- Provider availability
- 100.00% (13 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11958 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:01:56.000Z
|
| 11 |
zero-g/0gm-1.0-35b-a3b
zero-g
|
100.00% |
1908 ms |
Not measured
0 samples, warming |
1111 with TTFT |
More
- Provider availability
- 100.00% (11 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4281 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:18:47.000Z
|
| 12 |
deepseek/deepseek-v4.1-flash
together
|
100.00% |
1944 ms |
Not measured
0 samples, warming |
187 with TTFT |
More
- Provider availability
- 100.00% (18 samples)
- Within deadline
- 57.14%
- Capacity accepted
- 100.00%
- p95 TTFT
- 25612 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:40:19.784Z
|
| 13 |
upstage/solar-pro3
upstage
|
100.00% |
1984 ms |
Not measured
0 samples, warming |
1111 with TTFT |
More
- Provider availability
- 100.00% (11 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4046 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:04:00.000Z
|
| 14 |
scaledown/summarize
scaledown
|
100.00% |
2061 ms |
Not measured
0 samples, warming |
108 with TTFT |
More
- Provider availability
- 100.00% (10 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4407 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:47:53.000Z
|
| 15 |
deepseek/deepseek-flash
deepseek
|
100.00% |
2072 ms |
Not measured
0 samples, warming |
1613 with TTFT |
More
- Provider availability
- 100.00% (16 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4144 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:30:42.000Z
|
| 16 |
openai/gpt-oss-120b
tinfoil
|
100.00% |
2076 ms |
97 tok/s
1 samples, warming |
547 with TTFT |
More
- Provider availability
- 100.00% (54 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3476 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:22:42.000Z
|
| 17 |
z-ai/glm-5.3
thinkingmachines
|
100.00% |
2399 ms |
Not measured
0 samples, warming |
1212 with TTFT |
More
- Provider availability
- 100.00% (12 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 10425 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:42:42.000Z
|
| 18 |
moonshotai/kimi-k3
relace
|
93.75% |
2435 ms |
107 tok/s
2 samples, warming |
1615 with TTFT |
More
- Provider availability
- 93.75% (16 samples)
- Within deadline
- 93.75%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5500 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:48:54.000Z
|
| 19 |
minimax/minimax-m2.5-highspeed
minimax
|
100.00% |
2439 ms |
Not measured
0 samples, warming |
1010 with TTFT |
More
- Provider availability
- 100.00% (10 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7801 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:09:39.000Z
|
| 20 |
stepfun/step-3.5-flash-2603
stepfun
|
100.00% |
2498 ms |
Not measured
0 samples, warming |
1212 with TTFT |
More
- Provider availability
- 100.00% (12 samples)
- Within deadline
- 91.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 21955 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:30:48.000Z
|
| 21 |
thinkingmachines/inkling
thinkingmachines
|
100.00% |
2699 ms |
77 tok/s
2 samples, warming |
1010 with TTFT |
More
- Provider availability
- 100.00% (10 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5602 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:09:42.000Z
|
| 22 |
stepfun/step-3.5-flash
stepfun
|
100.00% |
2789 ms |
Not measured
0 samples, warming |
1313 with TTFT |
More
- Provider availability
- 100.00% (13 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9814 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:30:47.000Z
|
| 23 |
perplexity/sonar
perplexity
|
100.00% |
3037 ms |
Not measured
0 samples, warming |
4141 with TTFT |
More
- Provider availability
- 100.00% (41 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4840 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:25:56.000Z
|
| 24 |
openai/gpt-5.6-luna
openai
|
100.00% |
3191 ms |
Not measured
0 samples, warming |
125 with TTFT |
More
- Provider availability
- 100.00% (12 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3585 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:27:11.456Z
|
| 25 |
deepseek/deepseek-v4-flash-0731
deepinfra
|
99.28% |
3315 ms |
32 tok/s
1 samples, warming |
138137 with TTFT |
More
- Provider availability
- 99.28% (138 samples)
- Within deadline
- 99.28%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11333 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:37:08.000Z
|
| 26 |
deepseek/deepseek-v4.1-flash
deepinfra
|
100.00% |
3582 ms |
Not measured
0 samples, warming |
333291 with TTFT |
More
- Provider availability
- 100.00% (333 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9424 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:40:50.112Z
|
| 27 |
scaledown/classify
scaledown
2 excluded
|
100.00% |
3634 ms |
Not measured
0 samples, warming |
1212 with TTFT |
More
- Provider availability
- 100.00% (12 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 17757 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- provider_error: 2
- Last seen
- 2026-09-17T10:08:25.000Z
|
| 28 |
moonshotai/kimi-k2.6
kimi
|
100.00% |
3655 ms |
Not measured
0 samples, warming |
1313 with TTFT |
More
- Provider availability
- 100.00% (13 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 15938 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:57:46.000Z
|
| 29 |
deepseek/deepseek-v4-flash-0731
nebius
|
98.75% |
3745 ms |
Not measured
0 samples, warming |
8079 with TTFT |
More
- Provider availability
- 98.75% (80 samples)
- Within deadline
- 98.75%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8386 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:34:34.002Z
|
| 30 |
xiaomi/mimo-v2.5-pro
xiaomi
|
100.00% |
3762 ms |
Not measured
0 samples, warming |
1212 with TTFT |
More
- Provider availability
- 100.00% (12 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9319 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:07:08.000Z
|
| 31 |
deepseek/deepseek-v4.1-flash
tinfoil
|
100.00% |
3927 ms |
Not measured
0 samples, warming |
10883 with TTFT |
More
- Provider availability
- 100.00% (108 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9301 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:18:58.000Z
|
| 32 |
z-ai/glm-5.2
phala
|
63.64% |
4367 ms |
21 tok/s
2 samples, warming |
117 with TTFT |
More
- Provider availability
- 63.64% (11 samples)
- Within deadline
- 63.64%
- Capacity accepted
- 100.00%
- p95 TTFT
- 10934 ms
- Failure owner
- provider: 4
- Errors
- TimeoutError: 4
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:43:47.000Z
|
| 33 |
google/gemini-3.1-pro-preview
google-ai-studio
|
100.00% |
4801 ms |
Not measured
0 samples, warming |
3504 with TTFT |
More
- Provider availability
- 100.00% (350 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5783 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:42:51.000Z
|
| 34 |
sakana-ai/fugu-ultra-v1.1
sakana
11 excluded
|
66.67% |
6353 ms |
Not measured
0 samples, warming |
2222 with TTFT |
More
- Provider availability
- 100.00% (22 samples)
- Within deadline
- 95.45%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8971 ms
- Failure owner
- trustedrouter: 11
- Errors
- None
- Excluded from provider availability
- router_error: 11
- Last seen
- 2026-09-17T12:15:59.000Z
|
| 35 |
moonshotai/kimi-k3
kimi
|
100.00% |
8270 ms |
21 tok/s
2 samples, warming |
9927 with TTFT |
More
- Provider availability
- 100.00% (99 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11636 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:26:59.661Z
|
| 36 |
z-ai/glm-5.3-flash
zai
|
100.00% |
8653 ms |
Not measured
0 samples, warming |
3331 with TTFT |
More
- Provider availability
- 100.00% (33 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11693 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:30:39.533Z
|
| 37 |
stealth/union-alpha
openrouter
|
96.40% |
10345 ms |
Not measured
0 samples, warming |
500471 with TTFT |
More
- Provider availability
- 96.40% (500 samples)
- Within deadline
- 75.66%
- Capacity accepted
- 98.00%
- p95 TTFT
- 42459 ms
- Failure owner
- provider: 18
- Errors
- provider_error: 18
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:41:00.000Z
|
| 38 |
z-ai/glm-5.3
fireworks
|
94.12% |
23042 ms |
Not measured
0 samples, warming |
1716 with TTFT |
More
- Provider availability
- 94.12% (17 samples)
- Within deadline
- 94.12%
- Capacity accepted
- 100.00%
- p95 TTFT
- 29423 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:05:04.000Z
|
| 39 |
deepseek/deepseek-v4-flash-0731
fireworks
|
100.00% |
23967 ms |
192 tok/s
1 samples, warming |
1311 with TTFT |
More
- Provider availability
- 100.00% (13 samples)
- Within deadline
- 9.09%
- Capacity accepted
- 100.00%
- p95 TTFT
- 32631 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:27:16.000Z
|
| — |
morph/morph-v3-large
morph
warming
|
100.00% |
700 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2009 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:42:48.000Z
|
| — |
minimax/minimax-m3
together
warming
|
100.00% |
730 ms |
100 tok/s
2 samples, warming |
222 with TTFT |
More
- Provider availability
- 100.00% (22 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 788 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:06:00.041Z
|
| — |
meta-llama/llama-3.1-8b-instruct
wandb
warming
|
100.00% |
746 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 844 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:43:51.000Z
|
| — |
google/gemini-3.5-flash-lite
google-vertex
warming
|
100.00% |
773 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3606 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:49:40.000Z
|
| — |
openai/gpt-4.1-mini
openai
warming
|
100.00% |
775 ms |
Not measured
0 samples, warming |
482 with TTFT |
More
- Provider availability
- 100.00% (48 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1361 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:18:38.000Z
|
| — |
mistralai/mistral-nemo
mistral
warming
|
100.00% |
812 ms |
56 tok/s
2 samples, warming |
321 with TTFT |
More
- Provider availability
- 100.00% (32 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 812 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:29:13.996Z
|
| — |
qwen/qwen3.6-27b
deepinfra
warming
|
100.00% |
814 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 814 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:58:39.000Z
|
| — |
z-ai/glm-5.3-fast
fireworks
warming
|
100.00% |
832 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 832 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:23:46.000Z
|
| — |
z-ai/glm-5.3
wafer
warming
|
100.00% |
849 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1198 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:08:21.000Z
|
| — |
z-ai/glm-4.7-flash
cloudflare-workers-ai
warming
|
100.00% |
863 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3088 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:11:43.000Z
|
| — |
morph/morph-v3-fast
morph
warming
|
100.00% |
865 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1441 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:09:52.000Z
|
| — |
undi95/remm-slerp-l2-13b
mancer
warming
|
100.00% |
879 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1201 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:15:48.000Z
|
| — |
google/gemini-3.1-flash-lite
google-ai-studio
warming
|
100.00% |
890 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3519 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:10:50.000Z
|
| — |
mistralai/mistral-small-3.2-24b-instruct-2506
scaleway
warming
|
100.00% |
898 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2889 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:40:18.000Z
|
| — |
moonshotai/kimi-k3-fast
fireworks
warming
|
100.00% |
907 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 907 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:45:41.000Z
|
| — |
z-ai/glm-5.3
pearl
warming
|
100.00% |
925 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 925 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:37:48.000Z
|
| — |
qwen/qwen3.6-35b-a3b
deepinfra
warming
|
100.00% |
944 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 944 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:24:44.000Z
|
| — |
deepseek/deepseek-v4-flash
parasail
warming
|
100.00% |
953 ms |
95 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2086 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:13:00.000Z
|
| — |
moonshotai/kimi-k2.7-code
fireworks
warming
|
100.00% |
959 ms |
74 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 959 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:42:44.000Z
|
| — |
minimax/minimax-m3
fireworks
warming
|
100.00% |
987 ms |
220 tok/s
1 samples, warming |
1672 with TTFT |
More
- Provider availability
- 100.00% (167 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4050 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:37:24.000Z
|
| — |
NousResearch/Hermes-4-405B
nebius
warming
|
100.00% |
991 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1423 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:07:26.000Z
|
| — |
moonshotai/kimi-k2.6
wafer
warming
|
100.00% |
995 ms |
156 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2236 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:42:40.000Z
|
| — |
zai-org/autoglm-phone-9b-multilingual
novita
warming
|
100.00% |
1000 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1000 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:50.000Z
|
| — |
minimax/minimax-m2.5
digitalocean
warming
|
100.00% |
1002 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3916 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:07:56.000Z
|
| — |
nvidia/nemotron-3-super-120b-a12b
nvidia-nim
warming
|
100.00% |
1003 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1003 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:15:46.000Z
|
| — |
qwen/qwen3.8-27b
telnyx
warming
|
100.00% |
1009 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3362 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:27:49.000Z
|
| — |
google/gemma-4-31b-it
lightning
warming
|
100.00% |
1014 ms |
190 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1014 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:49:31.000Z
|
| — |
openai/gpt-oss-20b
io-net
warming
|
100.00% |
1018 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1480 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:30:47.000Z
|
| — |
google/gemini-3.1-flash-image-preview
google-ai-studio
warming
|
100.00% |
1024 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1922 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:52:50.000Z
|
| — |
mistralai/ministral-3-14b-instruct
digitalocean
warming
|
100.00% |
1038 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4162 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:37:49.000Z
|
| — |
openai/gpt-oss-120b
fireworks
warming
|
100.00% |
1043 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1043 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:26:56.000Z
|
| — |
google/gemma-4-26b-a4b-it
cloudflare-workers-ai
warming
|
100.00% |
1048 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1048 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:41:31.000Z
|
| — |
z-ai/glm-5.3-flash
together
warming
|
100.00% |
1058 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1355 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:42:51.000Z
|
| — |
deepseek/deepseek-v4-flash
deepinfra
warming
|
100.00% |
1061 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1061 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:23:33.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
databricks
warming
|
100.00% |
1067 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1523 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:54:42.000Z
|
| — |
qwen/qwen3-32b
alibaba
warming
|
100.00% |
1095 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1095 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:04:35.000Z
|
| — |
deepseek/deepseek-v4-flash
featherless
warming
|
100.00% |
1105 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3394 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:33:44.000Z
|
| — |
nvidia/nemotron-3-ultra-550b-a55b
fireworks
warming
|
100.00% |
1108 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5040 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:30:47.000Z
|
| — |
openai/gpt-oss-120b
io-net
warming
|
100.00% |
1110 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1110 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:39:44.000Z
|
| — |
qwen/qwen3.5-397b-a17b
digitalocean
warming
|
66.67% |
1112 ms |
Not measured
0 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3220 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:28:02.000Z
|
| — |
meta-llama/llama-3.1-8b-instruct-fp8
cloudflare-workers-ai
warming
|
100.00% |
1120 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1496 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:21:45.000Z
|
| — |
z-ai/glm-5.1
friendli
warming
|
100.00% |
1122 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3681 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:21:46.000Z
|
| — |
deepseek/deepseek-v4-flash
morph
warming
|
66.67% |
1126 ms |
51 tok/s
1 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 66.67%
- p95 TTFT
- 2006 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:25:25.000Z
|
| — |
qwen/qwen3-coder-30b-a3b-instruct
scaleway
warming
|
100.00% |
1128 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1128 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:45:44.000Z
|
| — |
z-ai/glm-5.3
nvidia-nim
warming
|
100.00% |
1134 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3052 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:02:19.000Z
|
| — |
minimax/minimax-m3
parasail
warming
|
100.00% |
1137 ms |
134 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3361 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:56:08.000Z
|
| — |
z-ai/glm-5.2
together
warming
|
100.00% |
1141 ms |
104 tok/s
2 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3678 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:41:46.000Z
|
| — |
x-ai/grok-build-0.1
grok
warming
|
100.00% |
1145 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1477 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:29:14.000Z
|
| — |
qwen/qwen3.6-35b-a3b
io-net
warming
|
100.00% |
1157 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1157 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:24:41.000Z
|
| — |
google/gemma-4-31b-it
regolo
warming
|
100.00% |
1162 ms |
90 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1162 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:23:50.000Z
|
| — |
google/gemma-4-31b-it
friendli
warming
|
100.00% |
1163 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3690 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:25:37.000Z
|
| — |
qwen/qwen3-next-80b-a3b-instruct
io-net
warming
|
100.00% |
1173 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1173 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:40:51.000Z
|
| — |
qwen/qwen3.5-flash
atlas-cloud
warming
|
100.00% |
1180 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1180 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:57:51.000Z
|
| — |
z-ai/glm-5.2
fireworks
warming
|
100.00% |
1194 ms |
71 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1399 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:11:31.000Z
|
| — |
qwen/qwen3.8-27b
cerebras
warming
|
100.00% |
1198 ms |
Not measured
0 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3277 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:31:11.000Z
|
| — |
google/gemma-3-27b-it
nebius
warming
|
100.00% |
1202 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2024 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:39:44.000Z
|
| — |
mistralai/mistral-small-24b-instruct-2501
deepinfra
warming
|
100.00% |
1203 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1203 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:40:48.000Z
|
| — |
meta-llama/llama-3.2-11b-vision-instruct
nvidia-nim
warming
|
100.00% |
1208 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1208 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:53:21.000Z
|
| — |
bsc-lt/alia-40b-instruct-2601
nextbit
warming
|
100.00% |
1218 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1488 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:24:45.000Z
|
| — |
cerebras/gpt-oss-120b
cerebras
warming
|
100.00% |
1224 ms |
191 tok/s
2 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3553 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:21:51.000Z
|
| — |
qwen/qwen3.8-2.4t-a95b
together
warming
|
100.00% |
1227 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2072 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:32:10.000Z
|
| — |
moonshotai/kimi-k2.7-code
siliconflow
warming
|
100.00% |
1229 ms |
33 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1901 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:49:31.000Z
|
| — |
qwen/qwen-mt-flash
alibaba
warming
|
100.00% |
1229 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1229 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:29:06.000Z
|
| — |
google/gemma-4-26b-a4b-it
nextbit
warming
|
100.00% |
1238 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1483 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:54:48.000Z
|
| — |
nvidia/nemotron-3-ultra-550b
digitalocean
warming
|
100.00% |
1261 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1720 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:56:06.000Z
|
| — |
moonshotai/kimi-k2.7-code
atlas-cloud
warming
|
100.00% |
1270 ms |
62 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3351 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:30:43.000Z
|
| — |
x-ai/grok-4.3
grok
warming
|
100.00% |
1271 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4510 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:09:46.000Z
|
| — |
google/gemini-3.5-flash
google-vertex
warming
|
100.00% |
1278 ms |
107 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3402 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:45:39.000Z
|
| — |
minimax/minimax-m2.7
telnyx
warming
|
100.00% |
1278 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1769 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:49:42.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
pearl
warming
|
100.00% |
1279 ms |
174 tok/s
1 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3498 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:24:49.000Z
|
| — |
google/gemini-3-flash-preview
google-vertex
warming
|
100.00% |
1281 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1704 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:16:34.000Z
|
| — |
z-ai/glm-5.3
siliconflow
warming
|
100.00% |
1281 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1890 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:46:35.000Z
|
| — |
qwen/qwen2.5-coder-32b-instruct
cloudflare-workers-ai
warming
|
100.00% |
1288 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1510 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:10:42.000Z
|
| — |
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
io-net
warming
|
100.00% |
1290 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1290 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:15:50.000Z
|
| — |
tencent/hy3
deepinfra
warming
|
100.00% |
1296 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1296 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:12:41.000Z
|
| — |
openai/gpt-oss-20b
novita
warming
|
100.00% |
1300 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1300 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:50:21.000Z
|
| — |
qwen/qwen3-235b-a22b-instruct-2507
alibaba
warming
|
100.00% |
1307 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1307 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:28:35.000Z
|
| — |
deepseek/deepseek-v3.2
friendli
warming
|
100.00% |
1308 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5341 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:33:44.000Z
|
| — |
z-ai/glm-5.3-flash
sail-research
warming
|
50.00% |
1308 ms |
Not measured
0 samples, warming |
21 with TTFT |
More
- Provider availability
- 50.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1308 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:02:20.000Z
|
| — |
mistralai/mistral-large
mistral
warming
|
100.00% |
1312 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3630 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:54:39.000Z
|
| — |
qwen/qwen3.8-27b
pearl
warming
|
100.00% |
1319 ms |
Not measured
0 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3849 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:36:46.000Z
|
| — |
openai/gpt-4o-mini
openai
warming
|
100.00% |
1325 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1325 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:22:56.000Z
|
| — |
google/gemini-2.5-flash
lightning
warming
|
100.00% |
1335 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1335 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:08:48.000Z
|
| — |
google/gemini-3.1-flash-lite
google-vertex
warming
|
100.00% |
1335 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1419 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:00:39.000Z
|
| — |
openai/gpt-oss-120b
databricks
warming
|
100.00% |
1339 ms |
57 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4779 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:03:42.000Z
|
| — |
meta-llama/llama-4-maverick
databricks
warming
|
100.00% |
1340 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1611 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:38:28.000Z
|
| — |
deepseek/deepseek-v4.1-flash
telnyx
warming
|
100.00% |
1344 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1344 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:48:49.000Z
|
| — |
meta-llama/llama-3.2-3b-instruct
cloudflare-workers-ai
warming
|
100.00% |
1353 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1611 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:12:44.000Z
|
| — |
deepseek/deepseek-v4-pro
baseten
warming
|
100.00% |
1355 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2396 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:09:44.000Z
|
| — |
minimax/minimax-m2.5
friendli
warming
|
100.00% |
1355 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1471 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:36:51.000Z
|
| — |
swiss-ai/apertus-70b-instruct
regolo
warming
|
100.00% |
1356 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3308 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:41:09.000Z
|
| — |
qwen/qwen3.5-122b-a10b
siliconflow
warming
|
100.00% |
1370 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3433 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:21:52.000Z
|
| — |
gryphe/mythomax-l2-13b
mancer
warming
|
100.00% |
1372 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2975 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:04:03.000Z
|
| — |
qwen/qwen3.6-35b-a3b
engy
warming
|
100.00% |
1375 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3099 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:57:39.000Z
|
| — |
mistralai/mistral-medium-3.5-128b
scaleway
warming
|
100.00% |
1377 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1536 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:21:49.000Z
|
| — |
lightning-ai/deepseek-v4-pro
lightning
warming
|
100.00% |
1380 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2746 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:01:37.000Z
|
| — |
nvidia/nemotron-3_5-lightning
nebius
warming
|
100.00% |
1381 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1381 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:15:55.000Z
|
| — |
z-ai/glm-4.7-flash
venice
warming
|
100.00% |
1384 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 13831 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:36:57.000Z
|
| — |
x-ai/grok-4.20-non-reasoning
azure
warming
|
100.00% |
1397 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3865 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:51:11.000Z
|
| — |
deepseek/deepseek-v3.2
sambanova
warming
|
100.00% |
1398 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 20506 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:57:40.000Z
|
| — |
nvidia/nemotron-nano-12b-v2-vl
digitalocean
warming
|
100.00% |
1398 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1602 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:09:49.000Z
|
| — |
qwen/qwen-3-8-2-4t-a95b
venice
warming
|
100.00% |
1398 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1398 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:43:59.000Z
|
| — |
google/gemini-3.5-flash-lite
google-ai-studio
warming
|
100.00% |
1404 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1468 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:39:46.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
wandb
warming
|
100.00% |
1409 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3703 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:28:41.000Z
|
| — |
thinkingmachines/inkling-small
baseten
warming
|
100.00% |
1411 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1411 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:03:44.000Z
|
| — |
openai/gpt-4.1-nano
openai
warming
|
100.00% |
1421 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1421 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:55:06.000Z
|
| — |
minimax/minimax-m3
featherless
warming
|
100.00% |
1425 ms |
229 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1425 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:22:36.000Z
|
| — |
openai/gpt-oss-120b
mancer
warming
|
100.00% |
1425 ms |
32 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 12702 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:51:42.000Z
|
| — |
qwen/qwen3.6-35b-a3b
akashml
warming
|
100.00% |
1426 ms |
Not measured
0 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3991 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:55:01.000Z
|
| — |
openai/gpt-oss-120b
cerebras
warming
|
100.00% |
1427 ms |
185 tok/s
1 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3441 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:25:01.000Z
|
| — |
z-ai/glm-5.3
akashml
warming
|
100.00% |
1428 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4489 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:39:41.000Z
|
| — |
qwen/qwen3-235b-a22b-instruct-2507
novita
warming
|
100.00% |
1429 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1429 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:09:47.000Z
|
| — |
z-ai/glm-5.3
tinfoil
warming
|
100.00% |
1443 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 25451 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:07:56.000Z
|
| — |
mistralai/mistral-small-3.1-24b-instruct
cloudflare-workers-ai
warming
|
100.00% |
1445 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1445 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:11:54.000Z
|
| — |
x-ai/grok-4.20-reasoning
grok
warming
|
100.00% |
1449 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3292 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:29:32.000Z
|
| — |
qwen/qwen-flash
alibaba
warming
|
100.00% |
1458 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1787 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:08:22.000Z
|
| — |
cerebras/qwen-3.8-27b
cerebras
warming
|
100.00% |
1463 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3335 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:09:46.000Z
|
| — |
google/gemma-3-12b-it
databricks
warming
|
100.00% |
1474 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1627 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:45:43.000Z
|
| — |
x-ai/grok-4.6
grok
warming
|
100.00% |
1478 ms |
42 tok/s
1 samples, warming |
99 with TTFT |
More
- Provider availability
- 100.00% (9 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4513 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:37:23.000Z
|
| — |
qwen/qwen3-235b-a22b-instruct-2507
nscale
warming
|
100.00% |
1482 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1482 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:16:55.000Z
|
| — |
qwen/qwen3.7-plus
alibaba
warming
|
100.00% |
1483 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1483 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:42:45.000Z
|
| — |
z-ai/glm-5.1
telnyx
warming
|
100.00% |
1484 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1484 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:43:32.000Z
|
| — |
qwen/qwen3.8-flash-next
pearl
warming
|
100.00% |
1485 ms |
Not measured
0 samples, warming |
87 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1711 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:50:13.000Z
|
| — |
deepseek/deepseek-v4.1-flash
makora
warming
|
100.00% |
1489 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2717 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:24:46.000Z
|
| — |
mistralai/mistral-nemo-instruct-2407
deepinfra
warming
|
100.00% |
1495 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1495 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:36:42.000Z
|
| — |
qwen/qwen2.5-coder-32b-instruct
nscale
warming
|
100.00% |
1531 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3087 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:27:48.000Z
|
| — |
deepseek-ai/DeepSeek-V4-Pro
nebius
warming
|
100.00% |
1533 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4254 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:40:18.000Z
|
| — |
deepseek/deepseek-v4-flash
siliconflow
warming
|
100.00% |
1533 ms |
45 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1533 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:22:21.000Z
|
| — |
qwen/qwen-plus-2025-12-01
alibaba
warming
|
100.00% |
1536 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1536 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:33:46.000Z
|
| — |
anthropic/claude-opus-4.8
anthropic
warming
|
100.00% |
1538 ms |
91 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1916 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:29:53.000Z
|
| — |
mistralai/pixtral-12b-2409
scaleway
warming
|
100.00% |
1538 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1555 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:45:47.000Z
|
| — |
google/gemini-2.5-flash
google-vertex
warming
|
100.00% |
1541 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1543 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:55:42.000Z
|
| — |
openai/gpt-4-turbo
openai
warming
|
100.00% |
1541 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3380 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:00:50.000Z
|
| — |
poolside/laguna-xs-2.1
nvidia-nim
warming
|
33.33% |
1553 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 33.33% (3 samples)
- Within deadline
- 33.33%
- Capacity accepted
- 66.67%
- p95 TTFT
- 1553 ms
- Failure owner
- provider: 2
- Errors
- empty_stream: 1, provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:41:13.000Z
|
| — |
qwen/qwen-plus-2025-07-28
alibaba
warming
|
100.00% |
1554 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1554 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:24:41.000Z
|
| — |
openai/gpt-5.1
openai
warming
|
100.00% |
1559 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1559 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:24:45.000Z
|
| — |
qwen/qwen2.5-coder-3b-instruct
nscale
warming
|
100.00% |
1560 ms |
Not measured
0 samples, warming |
42 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1706 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:02:55.000Z
|
| — |
qwen/qwen2.5-vl-72b-instruct
parasail
warming
|
100.00% |
1566 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1566 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:53:08.000Z
|
| — |
qwen/qwen3-235b-a22b
nscale
warming
|
100.00% |
1568 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5613 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:23:35.000Z
|
| — |
google/gemma-2b-it
telnyx
warming
|
100.00% |
1571 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3545 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:52:26.000Z
|
| — |
google/gemini-3.7-flash
google-vertex
warming
|
100.00% |
1574 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2117 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:25:25.000Z
|
| — |
openai/gpt-oss-120b
nebius
warming
|
100.00% |
1581 ms |
158 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1581 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:04:46.000Z
|
| — |
z-ai/glm-5.2
atlas-cloud
warming
|
100.00% |
1582 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1582 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:54.000Z
|
| — |
zai-org/glm-4.6v
novita
warming
|
100.00% |
1584 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1584 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:25:39.000Z
|
| — |
google/gemma-4-26b-a4b-it
novita
warming
|
100.00% |
1592 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1592 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:50:46.000Z
|
| — |
deepseek/deepseek-v4-pro-0813
fireworks
warming
|
100.00% |
1595 ms |
57 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1595 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:12:34.000Z
|
| — |
qwen/qwen3-vl-30b-a3b-instruct
novita
warming
|
100.00% |
1596 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1596 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:22:41.000Z
|
| — |
moonshotai/kimi-k3
telnyx
warming
|
100.00% |
1597 ms |
26 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1597 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:00:37.000Z
|
| — |
z-ai/glm-5.2
morph
warming
|
85.71% |
1600 ms |
68 tok/s
2 samples, warming |
76 with TTFT |
More
- Provider availability
- 85.71% (7 samples)
- Within deadline
- 85.71%
- Capacity accepted
- 85.71%
- p95 TTFT
- 4945 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:45:47.000Z
|
| — |
google/gemma-4-31b-it-nvfp4
sail-research
warming
|
100.00% |
1602 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1711 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:58:49.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
mancer
warming
|
100.00% |
1610 ms |
Not measured
0 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3174 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:30:44.000Z
|
| — |
qwen/qwen3-vl-flash
alibaba
warming
|
100.00% |
1613 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1613 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:45:43.000Z
|
| — |
z-ai/glm-5.3-flash
tinfoil
warming
|
50.00% |
1615 ms |
Not measured
0 samples, warming |
21 with TTFT |
More
- Provider availability
- 50.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 50.00%
- p95 TTFT
- 1615 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:06:47.000Z
|
| — |
z-ai/glm-5.2
engy
warming
|
100.00% |
1616 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2040 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:08:08.000Z
|
| — |
qwen/qwen3-14b
nscale
warming
|
100.00% |
1620 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2277 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:25:54.000Z
|
| — |
z-ai/glm-5.2
friendli
warming
|
100.00% |
1623 ms |
120 tok/s
2 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3728 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:37:32.000Z
|
| — |
openai/gpt-5.5-2026-04-23
lightning
warming
|
100.00% |
1629 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2037 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:46:11.000Z
|
| — |
deepseek/deepseek-v4-flash-0731-fast
wafer
warming
|
100.00% |
1633 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3107 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:18:46.000Z
|
| — |
qwen/qwen3-4b-instruct-2507
nscale
warming
|
100.00% |
1641 ms |
Not measured
0 samples, warming |
41 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1641 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:46:44.194Z
|
| — |
moonshotai/kimi-k2.6
baseten
warming
|
100.00% |
1652 ms |
146 tok/s
1 samples, warming |
53 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2992 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:05:45.833Z
|
| — |
openai/gpt-oss-120b
nscale
warming
|
100.00% |
1653 ms |
92 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3873 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:47:16.000Z
|
| — |
deepseek/deepseek-v4.1-flash
baseten
warming
|
100.00% |
1657 ms |
Not measured
0 samples, warming |
21 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1657 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:04:48.373Z
|
| — |
mistralai/mistral-small-2603
mistral
warming
|
100.00% |
1657 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3121 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:37:59.000Z
|
| — |
openai/gpt-oss-120b
scaleway
warming
|
100.00% |
1662 ms |
91 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3798 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:21:44.000Z
|
| — |
openai/gpt-oss-120b
regolo
warming
|
100.00% |
1665 ms |
125 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1665 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:16:55.000Z
|
| — |
thinkingmachines/inkling-small
thinkingmachines
warming
|
100.00% |
1667 ms |
Not measured
0 samples, warming |
99 with TTFT |
More
- Provider availability
- 100.00% (9 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3954 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:50:45.000Z
|
| — |
deepseek/deepseek-v4.1-flash
nebius
warming
|
100.00% |
1670 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1670 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:34:43.000Z
|
| — |
qwen/qwen3.8-27b
regolo
warming
|
80.00% |
1675 ms |
Not measured
0 samples, warming |
54 with TTFT |
More
- Provider availability
- 80.00% (5 samples)
- Within deadline
- 80.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3081 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:47:31.000Z
|
| — |
x-ai/grok-4.3
atlas-cloud
warming
|
100.00% |
1685 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1685 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:15:50.000Z
|
| — |
qwen/qwen3.8-27b
engy
warming
|
100.00% |
1686 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1862 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:14:05.000Z
|
| — |
meta-llama/llama-4-scout-17b-16e-instruct
cloudflare-workers-ai
warming
|
100.00% |
1690 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3228 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:23:40.000Z
|
| — |
undi95/remm-slerp-l2-13b
nextbit
warming
|
100.00% |
1694 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2880 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:34:44.000Z
|
| — |
deepseek/deepseek-v4p1-flash
fireworks
warming
|
100.00% |
1696 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3608 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:48:36.043Z
|
| — |
qwen/qwen3.8-max
fireworks
warming
|
100.00% |
1710 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1806 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:39:42.000Z
|
| — |
thedrummer/skyfall-36b-v2
parasail
warming
|
100.00% |
1730 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1730 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:47:12.000Z
|
| — |
google/gemma-4-26b-a4b-it
siliconflow
warming
|
100.00% |
1734 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1734 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:51:04.000Z
|
| — |
moonshotai/kimi-k2.7-code
baseten
warming
|
100.00% |
1735 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3698 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:23:44.000Z
|
| — |
openai/gpt-oss-120b
siliconflow
warming
|
100.00% |
1735 ms |
102 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2176 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:32:28.000Z
|
| — |
qwen/qwen3.5-27b
alibaba
warming
|
100.00% |
1735 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1735 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:28:36.000Z
|
| — |
x-ai/grok-4.20-reasoning
azure
warming
|
100.00% |
1753 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3749 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:18:51.000Z
|
| — |
moonshotai/kimi-k3
wafer
warming
|
100.00% |
1764 ms |
98 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2166 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:57:22.000Z
|
| — |
openai/gpt-oss-120b
sail-research
warming
|
100.00% |
1768 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4044 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:15:55.000Z
|
| — |
google/gemini-2.5-flash-lite
google-vertex
warming
|
100.00% |
1770 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2734 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:36:51.000Z
|
| — |
nvidia/nemotron-3-ultra-550b-a55b
wandb
warming
|
100.00% |
1774 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3779 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:32:10.000Z
|
| — |
qwen/qwen3.5-9b
venice
warming
|
100.00% |
1776 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1776 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:36:54.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
scaleway
warming
|
100.00% |
1785 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1785 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:45:49.000Z
|
| — |
google/gemma-3-27b-it
parasail
warming
|
100.00% |
1788 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4075 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:54:50.000Z
|
| — |
z-ai/glm-4.5-air
zai
warming
|
100.00% |
1788 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1788 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:27:50.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
together
warming
|
100.00% |
1794 ms |
Not measured
0 samples, warming |
41 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1794 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:38:05.706Z
|
| — |
z-ai/glm-5.3
engy
warming
|
100.00% |
1796 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3380 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:48:58.000Z
|
| — |
z-ai/glm-4.6
venice
warming
|
100.00% |
1798 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1798 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:03:44.000Z
|
| — |
meta-llama/llama-3.1-70b-instruct
telnyx
warming
|
100.00% |
1804 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3896 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:30:52.000Z
|
| — |
z-ai/glm-5.2
baseten
warming
|
100.00% |
1806 ms |
128 tok/s
1 samples, warming |
941 with TTFT |
More
- Provider availability
- 100.00% (94 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1806 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:17:29.000Z
|
| — |
minimax/minimax-m3
minimax
warming
|
100.00% |
1808 ms |
127 tok/s
2 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3585 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:10:50.000Z
|
| — |
minimax/minimax-m2
minimax
warming
|
100.00% |
1811 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3846 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:11:48.000Z
|
| — |
deepseek/deepseek-v3.1
wandb
warming
|
100.00% |
1812 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1812 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:51:52.000Z
|
| — |
mistralai/codestral-2508
mistral
warming
|
100.00% |
1823 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2970 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:36:44.000Z
|
| — |
deepseek/deepseek-v4-flash-0423
wafer
warming
|
25.00% |
1823 ms |
Not measured
0 samples, warming |
41 with TTFT |
More
- Provider availability
- 25.00% (4 samples)
- Within deadline
- 25.00%
- Capacity accepted
- 25.00%
- p95 TTFT
- 1823 ms
- Failure owner
- provider: 3
- Errors
- provider_error: 3
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:38:21.000Z
|
| — |
qwen/qwen3-next-80b-a3b-instruct
novita
warming
|
100.00% |
1832 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1832 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:37:21.000Z
|
| — |
qwen/qwen3-coder-flash
alibaba
warming
|
100.00% |
1833 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3146 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:40:14.000Z
|
| — |
anthropic/claude-sonnet-4.6
anthropic
warming
|
100.00% |
1836 ms |
Not measured
0 samples, warming |
142 with TTFT |
More
- Provider availability
- 100.00% (14 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5392 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:30:45.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
akashml
warming
|
100.00% |
1846 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3753 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:42:50.000Z
|
| — |
deepseek/deepseek-v4.1-flash
novita
warming
|
100.00% |
1863 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1863 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:03:46.000Z
|
| — |
qwen/qwen3.8-27b
wandb
warming
|
100.00% |
1867 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1867 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:36:43.000Z
|
| — |
scaledown/extract
scaledown
warming
2 excluded
|
100.00% |
1879 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4019 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- provider_error: 2
- Last seen
- 2026-09-17T07:21:40.000Z
|
| — |
openai/gpt-5.6-terra
atlas-cloud
warming
|
100.00% |
1881 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1881 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:31:09.000Z
|
| — |
qwen/qwen-plus
alibaba
warming
|
100.00% |
1885 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1885 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:17:06.000Z
|
| — |
moonshotai/kimi-k3
engy
warming
|
100.00% |
1890 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3810 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:32:22.000Z
|
| — |
openai/gpt-4
lightning
warming
|
100.00% |
1893 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1893 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:11:50.000Z
|
| — |
openai/gpt-4o
openai
warming
|
100.00% |
1901 ms |
Not measured
0 samples, warming |
43 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3742 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:00:31.838Z
|
| — |
qwen/qwen3.5-122b-a10b
alibaba
warming
|
100.00% |
1902 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2094 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:03:54.000Z
|
| — |
qwen/qwen3-8b
alibaba
warming
|
100.00% |
1908 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1908 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:07:40.000Z
|
| — |
qwen/qwen2.5-coder-7b-instruct
nscale
warming
|
100.00% |
1912 ms |
Not measured
0 samples, warming |
53 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3271 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:45:43.189Z
|
| — |
openai/gpt-5.2-2025-12-11
lightning
warming
|
100.00% |
1927 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1927 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:01:52.000Z
|
| — |
qwen/qwen3.6-35b-a3b
alibaba
warming
|
100.00% |
1932 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1932 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:29:00.000Z
|
| — |
minimax/minimax-m2.1-highspeed
minimax
warming
|
100.00% |
1956 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1956 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:45:46.000Z
|
| — |
qwen/qwen3.8-27b
akashml
warming
|
100.00% |
1963 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4043 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:21:41.000Z
|
| — |
google/gemma-4-26b-a4b-it
parasail
warming
|
100.00% |
1969 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2381 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:46:54.000Z
|
| — |
qwen/qwen3.7-plus-2026-05-26
alibaba
warming
|
100.00% |
1970 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1970 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:19:41.000Z
|
| — |
nousresearch/hermes-3-llama-3.1-405b
deepinfra
warming
|
100.00% |
1974 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1974 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:34:10.000Z
|
| — |
z-ai/glm-5
io-net
warming
|
100.00% |
1979 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3520 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:34:19.000Z
|
| — |
z-ai/glm-4.7
io-net
warming
|
100.00% |
1981 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5214 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:02:29.000Z
|
| — |
minimax/minimax-m3
siliconflow
warming
|
100.00% |
1985 ms |
82 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2156 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:41:52.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
siliconflow
warming
|
100.00% |
1987 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 1987 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:32:10.000Z
|
| — |
minimax/minimax-m2.7
minimax
warming
|
100.00% |
2001 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3739 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:41:11.000Z
|
| — |
openai/gpt-oss-20b
databricks
warming
|
100.00% |
2001 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3782 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:33:48.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
novita
warming
|
100.00% |
2004 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2004 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:43:15.000Z
|
| — |
openai/gpt-oss-20b
regolo
warming
|
100.00% |
2007 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2965 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:54:36.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
venice
warming
|
100.00% |
2009 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2475 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:00:52.000Z
|
| — |
z-ai/glm-4.7
baseten
warming
|
100.00% |
2013 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2448 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:30:40.000Z
|
| — |
deepseek/deepseek-v4-flash
io-net
warming
|
100.00% |
2016 ms |
107 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2016 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:25:52.000Z
|
| — |
z-ai/glm-4.5v
zai
warming
|
100.00% |
2024 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4869 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:22:25.000Z
|
| — |
google/gemma-4-12b-it
sail-research
warming
|
100.00% |
2025 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2842 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:36:48.000Z
|
| — |
qwen/qwen3.5-35b-a3b
alibaba
warming
|
100.00% |
2029 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2029 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:27:53.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
inceptron
warming
|
100.00% |
2037 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2037 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:56:31.000Z
|
| — |
anthropic/claude-opus-4.7
anthropic
warming
|
100.00% |
2039 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6251 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:15:44.000Z
|
| — |
meta-llama/llama-4-scout-17b-16e-instruct
novita
warming
|
100.00% |
2045 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2045 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:12:44.000Z
|
| — |
qwen/qwen3.6-35b-a3b
siliconflow
warming
|
100.00% |
2047 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3776 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:27:16.000Z
|
| — |
meta-llama/llama-3.3-70b
venice
warming
|
100.00% |
2048 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3768 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:21:51.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
featherless
warming
|
100.00% |
2049 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5021 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:00:51.000Z
|
| — |
google/gemini-3-flash-preview
google-ai-studio
warming
|
100.00% |
2066 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3462 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:05:22.000Z
|
| — |
anthropic/claude-opus-4.6
anthropic
warming
|
100.00% |
2070 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3311 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:43:11.000Z
|
| — |
google/gemma-4-31b-it
sambanova
warming
|
75.00% |
2071 ms |
119 tok/s
1 samples, warming |
86 with TTFT |
More
- Provider availability
- 75.00% (8 samples)
- Within deadline
- 75.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7216 ms
- Failure owner
- provider: 2
- Errors
- TimeoutError: 1, provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:44:12.000Z
|
| — |
google/gemma-4-31b-it
sail-research
warming
|
100.00% |
2073 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3731 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:22:45.000Z
|
| — |
microsoft/wizardlm-2-8x22b
novita
warming
|
100.00% |
2074 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2074 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:46:40.000Z
|
| — |
openai/gpt-oss-120b
together
warming
|
100.00% |
2078 ms |
106 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2078 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:52:17.000Z
|
| — |
z-ai/glm-5.3-fast
baseten
warming
|
100.00% |
2078 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2078 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:30:40.000Z
|
| — |
z-ai/glm-5.1
atlas-cloud
warming
|
100.00% |
2081 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2081 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:18:44.000Z
|
| — |
moonshotai/kimi-k2.6
parasail
warming
|
100.00% |
2085 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2085 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:17:13.000Z
|
| — |
openai/gpt-4o
lightning
warming
|
100.00% |
2086 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2086 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T12:54:59.000Z
|
| — |
deepseek/deepseek-v4-flash
makora
warming
|
100.00% |
2089 ms |
118 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3048 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:33:42.000Z
|
| — |
anthropic/claude-sonnet-4.5
anthropic
warming
|
100.00% |
2092 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2505 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:03:44.000Z
|
| — |
openai/gpt-6-astra
openai
warming
|
100.00% |
2093 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2093 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:28:52.000Z
|
| — |
openai/gpt-oss-20b
nscale
warming
|
100.00% |
2093 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2595 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:11:27.000Z
|
| — |
openai/gpt-4-0613
openai
warming
|
100.00% |
2096 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2096 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:15:48.000Z
|
| — |
google/gemma-4-26b-a4b-it
scaleway
warming
|
100.00% |
2110 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2156 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:45:54.000Z
|
| — |
qwen/qwen3-vl-8b-instruct
alibaba
warming
|
100.00% |
2136 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3709 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:33:40.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
sail-research
warming
|
100.00% |
2137 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4143 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:27:48.000Z
|
| — |
google/gemini-2.5-flash-lite-preview-06-17
lightning
warming
|
100.00% |
2137 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3620 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:49:23.000Z
|
| — |
google/gemini-3.8-flash
google-vertex
warming
|
100.00% |
2146 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2146 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:58:33.000Z
|
| — |
moonshotai/kimi-k2.5
nscale
warming
|
100.00% |
2161 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2390 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:35:32.000Z
|
| — |
z-ai/glm-5.3
sail-research
warming
|
100.00% |
2174 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3261 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:09:57.000Z
|
| — |
qwen/qwen3.6-27b
siliconflow
warming
|
100.00% |
2180 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3731 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:51:59.000Z
|
| — |
minimax/minimax-m3
novita
warming
|
100.00% |
2189 ms |
89 tok/s
2 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2189 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:56:55.000Z
|
| — |
z-ai/glm-4.6v
zai
warming
|
100.00% |
2192 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4443 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:16:55.000Z
|
| — |
moonshotai/kimi-k2.5
azure
warming
|
100.00% |
2196 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 10994 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:32:54.000Z
|
| — |
deepseek/deepseek-v4-pro
deepseek
warming
|
100.00% |
2197 ms |
Not measured
0 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4375 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:08:40.004Z
|
| — |
anthropic/claude-opus-5
anthropic
warming
|
100.00% |
2205 ms |
52 tok/s
2 samples, warming |
21 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2205 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:22:36.000Z
|
| — |
moonshotai/kimi-k2.6
telnyx
warming
|
100.00% |
2215 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4320 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:53.000Z
|
| — |
moonshotai/Kimi-K2.6
nebius
warming
|
100.00% |
2242 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2242 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:18:46.000Z
|
| — |
z-ai/glm-5.3
featherless
warming
|
100.00% |
2255 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2486 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:06:37.000Z
|
| — |
moonshotai/kimi-k2.7-code
kimi
warming
|
100.00% |
2262 ms |
68 tok/s
1 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3736 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:45:42.000Z
|
| — |
moonshotai/kimi-k3
nebius
warming
|
100.00% |
2298 ms |
87 tok/s
2 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3587 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:41:09.000Z
|
| — |
aion-labs/aion-rp-llama-3.1-8b
aion-labs
warming
|
100.00% |
2300 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3881 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:10:30.000Z
|
| — |
bytedance/seed-1.8
deepinfra
warming
|
100.00% |
2311 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2311 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:27:51.000Z
|
| — |
openai/gpt-5-nano
lightning
warming
|
100.00% |
2311 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2311 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:15:48.000Z
|
| — |
z-ai/glm-5.2
inceptron
warming
|
100.00% |
2313 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6788 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:53:29.000Z
|
| — |
deepseek/deepseek-v4-flash
digitalocean
warming
|
100.00% |
2321 ms |
43 tok/s
1 samples, warming |
91 with TTFT |
More
- Provider availability
- 100.00% (9 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2321 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:46:06.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
nvidia-nim
warming
|
33.33% |
2342 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 33.33% (3 samples)
- Within deadline
- 33.33%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2342 ms
- Failure owner
- provider: 2
- Errors
- TimeoutError: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:34:46.000Z
|
| — |
anthropic/claude-sonnet-5
anthropic
warming
|
100.00% |
2346 ms |
Not measured
0 samples, warming |
381 with TTFT |
More
- Provider availability
- 100.00% (38 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2346 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:15:41.000Z
|
| — |
z-ai/glm-5.3
zero-g
warming
|
100.00% |
2348 ms |
90 tok/s
1 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3389 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:03:44.000Z
|
| — |
deepseek/deepseek-v3.2-exp
atlas-cloud
warming
|
100.00% |
2349 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4608 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:42:48.000Z
|
| — |
deepseek/deepseek-v4-pro
siliconflow
warming
|
100.00% |
2357 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2357 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:54:45.000Z
|
| — |
deepseek/deepseek-v3.2
digitalocean
warming
|
100.00% |
2362 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3685 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:45:50.000Z
|
| — |
z-ai/glm-5.1
phala
warming
|
66.67% |
2377 ms |
Not measured
0 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6319 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:02:08.000Z
|
| — |
bytedance/doubao-seed-2.1-pro-260628
atlas-cloud
warming
|
100.00% |
2382 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3788 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:31:59.000Z
|
| — |
qwen/qwen3.5-122b-a10b
novita
warming
|
100.00% |
2390 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2390 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:15:51.000Z
|
| — |
upstage/solar-pro2
upstage
warming
|
100.00% |
2394 ms |
Not measured
0 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4576 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:02:25.000Z
|
| — |
nvidia/nemotron-3.5-lightning-30b-a3b
wandb
warming
|
100.00% |
2414 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3697 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:19:00.000Z
|
| — |
qwen/qwen3.6-35b-a3b
wandb
warming
|
100.00% |
2418 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4502 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:28:51.000Z
|
| — |
qwen/qwen-3-7-plus
venice
warming
|
100.00% |
2430 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2430 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:09:48.000Z
|
| — |
google/gemma-4-31b-it
digitalocean
warming
|
100.00% |
2432 ms |
61 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3416 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:03:40.000Z
|
| — |
qwen/qwen3.8-27b
io-net
warming
|
100.00% |
2432 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2432 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:30:55.000Z
|
| — |
moonshotai/kimi-k3
io-net
warming
|
100.00% |
2435 ms |
46 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2435 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:54:48.000Z
|
| — |
z-ai/glm-5.3
inceptron
warming
|
66.67% |
2472 ms |
Not measured
0 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11495 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:59:38.000Z
|
| — |
openai/gpt-3.5-turbo-1106
openai
warming
|
100.00% |
2476 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2476 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:30:49.000Z
|
| — |
deepseek/deepseek-v3.2
atlas-cloud
warming
|
100.00% |
2483 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2483 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:30:55.000Z
|
| — |
openai/o3-mini
openai
warming
|
100.00% |
2483 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4520 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:43:59.000Z
|
| — |
moonshotai/kimi-k2.6
novita
warming
|
100.00% |
2514 ms |
17 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2514 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:11:58.000Z
|
| — |
zai-org/GLM-5.2
nebius
warming
|
100.00% |
2527 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2527 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:42:41.000Z
|
| — |
openai/gpt-oss-20b
nvidia-nim
warming
|
75.00% |
2528 ms |
Not measured
0 samples, warming |
43 with TTFT |
More
- Provider availability
- 75.00% (4 samples)
- Within deadline
- 75.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3622 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:39:49.000Z
|
| — |
moonshotai/kimi-k2.6
digitalocean
warming
|
100.00% |
2530 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3384 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:00:59.000Z
|
| — |
nvidia/nemotron-3-nano-30b-a3b-bf16
nscale
warming
|
100.00% |
2543 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3661 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:04:23.000Z
|
| — |
deepseek/deepseek-v4-pro
alibaba
warming
|
100.00% |
2603 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2603 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:46:37.000Z
|
| — |
deepseek/deepseek-v4.1-flash
arcee
warming
|
100.00% |
2609 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4252 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:50:44.000Z
|
| — |
mistralai/mistral-small-2603
regolo
warming
|
100.00% |
2617 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2617 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:33:47.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
alibaba
warming
|
100.00% |
2628 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2628 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:52:16.000Z
|
| — |
deepseek/deepseek-v4-flash
mancer
warming
|
100.00% |
2637 ms |
80 tok/s
2 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3075 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:05:01.000Z
|
| — |
ibm-granite/granite-4.0-h-micro
cloudflare-workers-ai
warming
|
100.00% |
2666 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2666 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:45:41.000Z
|
| — |
moonshotai/kimi-k2-instruct
novita
warming
|
100.00% |
2696 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2696 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:19:52.000Z
|
| — |
z-ai/glm-5.3-flash
parasail
warming
|
100.00% |
2709 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5064 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:56:21.000Z
|
| — |
moonshotai/kimi-k3
gmi
warming
|
100.00% |
2710 ms |
26 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2710 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:50:42.000Z
|
| — |
deepseek/deepseek-v4-pro
gmi
warming
|
100.00% |
2719 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5471 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:03:45.000Z
|
| — |
qwen/qwen3.5-122b-a10b
regolo
warming
|
100.00% |
2739 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2911 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:27:52.000Z
|
| — |
moonshotai/kimi-k3
phala
warming
|
100.00% |
2749 ms |
35 tok/s
1 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 12176 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:32:00.000Z
|
| — |
moonshotai/kimi-k3
fireworks
warming
|
100.00% |
2755 ms |
66 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4700 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:15:57.000Z
|
| — |
moonshotai/kimi-k2.7-code
inceptron
warming
|
100.00% |
2762 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3312 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:57:45.000Z
|
| — |
openai/gpt-5-mini
openai
warming
|
100.00% |
2773 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2773 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:10:07.000Z
|
| — |
qwen/qwen3-14b
nextbit
warming
|
100.00% |
2775 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2775 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:27:48.000Z
|
| — |
scaledown/compress
scaledown
warming
2 excluded
|
100.00% |
2777 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3938 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- provider_error: 2
- Last seen
- 2026-09-17T08:15:47.000Z
|
| — |
openai/gpt-4-turbo
lightning
warming
|
100.00% |
2779 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5165 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:03:02.000Z
|
| — |
thedrummer/cydonia-24b-v4.1
parasail
warming
|
75.00% |
2781 ms |
Not measured
0 samples, warming |
43 with TTFT |
More
- Provider availability
- 75.00% (4 samples)
- Within deadline
- 75.00%
- Capacity accepted
- 75.00%
- p95 TTFT
- 5047 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:40:19.000Z
|
| — |
deepseek/deepseek-v3.1
sambanova
warming
|
80.00% |
2783 ms |
Not measured
0 samples, warming |
54 with TTFT |
More
- Provider availability
- 80.00% (5 samples)
- Within deadline
- 80.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4686 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:16:55.000Z
|
| — |
qwen/qwen3.5-9b
regolo
warming
|
100.00% |
2798 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5229 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:29:14.333Z
|
| — |
openai/gpt-5-mini
azure
warming
|
100.00% |
2814 ms |
Not measured
0 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4918 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:06:43.000Z
|
| — |
z-ai/glm-5.2
novita
warming
|
100.00% |
2827 ms |
79 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2827 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:56:32.000Z
|
| — |
z-ai/glm-5.3
telnyx
warming
|
100.00% |
2831 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2831 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:45:46.000Z
|
| — |
tencent/hy3
siliconflow
warming
|
100.00% |
2871 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4595 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:08:19.000Z
|
| — |
openai/gpt-5.6-terra
lightning
warming
|
100.00% |
2885 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2885 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:32:52.000Z
|
| — |
openai/gpt-oss-120b
wandb
warming
|
100.00% |
2914 ms |
53 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3145 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:16:58.000Z
|
| — |
openai/gpt-oss-120b
sambanova
warming
|
75.00% |
2915 ms |
43 tok/s
1 samples, warming |
43 with TTFT |
More
- Provider availability
- 75.00% (4 samples)
- Within deadline
- 75.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3607 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:58:53.000Z
|
| — |
qwen/qwen3.7-max
novita
warming
|
100.00% |
2920 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2920 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:43:22.000Z
|
| — |
qwen/qwen3-235b-a22b-instruct-2507
scaleway
warming
|
100.00% |
2924 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4522 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:48:52.000Z
|
| — |
z-ai/glm-5
siliconflow
warming
|
100.00% |
2936 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4405 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:36:46.000Z
|
| — |
deepseek/deepseek-v4-flash
arcee
warming
|
100.00% |
2941 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5706 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:06:45.000Z
|
| — |
z-ai/glm-5.3
arcee
warming
|
100.00% |
2948 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6777 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:39:43.000Z
|
| — |
z-ai/glm-5.3
friendli
warming
|
100.00% |
2962 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3151 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:12:43.000Z
|
| — |
openai/gpt-6-astra
lightning
warming
|
100.00% |
2973 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4427 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:15:44.000Z
|
| — |
deepseek/deepseek-v3.1
atlas-cloud
warming
|
100.00% |
2981 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 2981 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:39:43.000Z
|
| — |
openai/gpt-oss-120b-ultra
deepinfra
warming
|
100.00% |
3000 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3000 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:17:18.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
sambanova
warming
|
100.00% |
3006 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3532 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:39:46.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
io-net
warming
|
100.00% |
3013 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3689 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:00:45.000Z
|
| — |
stepfun/step-3.7-flash
stepfun
warming
|
100.00% |
3028 ms |
95 tok/s
2 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9097 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:17:00.000Z
|
| — |
z-ai/glm-5.2-fast
baseten
warming
|
100.00% |
3029 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3349 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:48:49.000Z
|
| — |
z-ai/glm-5.2-fast
fireworks
warming
|
100.00% |
3050 ms |
153 tok/s
1 samples, warming |
1592 with TTFT |
More
- Provider availability
- 100.00% (159 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3152 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:38:24.810Z
|
| — |
openai/gpt-4o-2024-05-13
openai
warming
|
100.00% |
3053 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3053 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:45:48.000Z
|
| — |
z-ai/glm-5.3-flash
engy
warming
|
100.00% |
3139 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3533 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:57:45.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
scaleway
warming
|
100.00% |
3142 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3142 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:15:56.000Z
|
| — |
qwen/qwen3.8-27b
featherless
warming
|
100.00% |
3152 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3152 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:54:54.000Z
|
| — |
sao10k/l3.3-70b-euryale-v2.3
nextbit
warming
|
80.00% |
3175 ms |
Not measured
0 samples, warming |
54 with TTFT |
More
- Provider availability
- 80.00% (5 samples)
- Within deadline
- 80.00%
- Capacity accepted
- 80.00%
- p95 TTFT
- 10386 ms
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:15:45.000Z
|
| — |
z-ai/glm-5.2
gmi
warming
|
100.00% |
3178 ms |
95 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7123 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:26:04.000Z
|
| — |
openbmb/MiniCPM-V-4_5
nebius
warming
|
100.00% |
3180 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3244 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:55:28.000Z
|
| — |
moonshotai/kimi-k2.6
sail-research
warming
|
100.00% |
3199 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4357 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:45:53.000Z
|
| — |
moonshotai/kimi-k3
tinfoil
warming
|
100.00% |
3204 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9026 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:37:09.000Z
|
| — |
z-ai/glm-5.1
venice
warming
|
100.00% |
3209 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4159 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:44:19.000Z
|
| — |
openai/gpt-5
openai
warming
|
100.00% |
3224 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4210 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:24:48.000Z
|
| — |
anthropic/claude-fable-5.1
anthropic
warming
|
100.00% |
3232 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3232 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:40:12.000Z
|
| — |
aisingapore/gemma-sea-lion-v4-27b-it
cloudflare-workers-ai
warming
|
100.00% |
3235 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3235 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:09:47.000Z
|
| — |
qwen/qwen3.6-35b-a3b
parasail
warming
|
100.00% |
3235 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3235 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:27:48.000Z
|
| — |
qwen/qwen3.8-27b
novita
warming
|
100.00% |
3247 ms |
Not measured
0 samples, warming |
92 with TTFT |
More
- Provider availability
- 100.00% (9 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3566 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:40:44.971Z
|
| — |
mistralai/mistral-nemo-instruct-2407
io-net
warming
|
100.00% |
3253 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3253 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:47:34.000Z
|
| — |
qwen/qwen3-coder-next
regolo
warming
|
100.00% |
3263 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3263 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:25:57.000Z
|
| — |
minimax/minimax-m2.7-highspeed
minimax
warming
|
100.00% |
3268 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4904 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:27:51.000Z
|
| — |
nvidia/nemotron-3-nano-omni
digitalocean
warming
|
100.00% |
3275 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3458 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:09:42.000Z
|
| — |
moonshotai/kimi-k2.7-code
azure
warming
|
100.00% |
3279 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5907 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:27:46.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
telnyx
warming
|
100.00% |
3285 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3695 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:44:21.000Z
|
| — |
qwen/qwen-mt-turbo
alibaba
warming
|
100.00% |
3301 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3301 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:56:25.000Z
|
| — |
deepseek/deepseek-v4-pro
digitalocean
warming
|
100.00% |
3304 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3534 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:42:40.000Z
|
| — |
deepseek/deepseek-v4.1-flash
featherless
warming
|
100.00% |
3306 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3306 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:08:12.000Z
|
| — |
z-ai/glm-5
zai
warming
|
100.00% |
3309 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4168 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:21:50.000Z
|
| — |
qwen/qwen3-30b-a3b-instruct-2507
wandb
warming
|
100.00% |
3316 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3316 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:29:16.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
nextbit
warming
|
100.00% |
3333 ms |
82 tok/s
2 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4629 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:19:23.000Z
|
| — |
meta-llama/llama-4-maverick
digitalocean
warming
|
100.00% |
3355 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3355 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:35:28.000Z
|
| — |
google/gemini-2.5-pro
google-vertex
warming
|
100.00% |
3359 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4305 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:33:45.000Z
|
| — |
bytedance/doubao-seed-2.0-lite-260428
atlas-cloud
warming
|
100.00% |
3363 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3363 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:36:50.000Z
|
| — |
z-ai/glm-5.3
zai
warming
|
100.00% |
3369 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4678 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:07:55.334Z
|
| — |
qwen/qwen3.5-122b-a10b
databricks
warming
|
100.00% |
3376 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5502 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:34:50.000Z
|
| — |
Qwen/Qwen3.5-397B-A17B
nebius
warming
|
100.00% |
3379 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3379 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:01:22.000Z
|
| — |
openai/gpt-oss-20b
wandb
warming
|
100.00% |
3379 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3379 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:19:46.000Z
|
| — |
z-ai/glm-5.2
digitalocean
warming
|
100.00% |
3379 ms |
40 tok/s
2 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3379 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:05:06.000Z
|
| — |
xiaomi/mimo-v2.5-pro
digitalocean
warming
|
100.00% |
3385 ms |
51 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3781 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:00:45.000Z
|
| — |
x-ai/grok-4.5
grok
warming
|
100.00% |
3388 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3920 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:11:31.000Z
|
| — |
qwen/qwen3.5-397b-a17b
scaleway
warming
|
100.00% |
3396 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 24586 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:51:49.000Z
|
| — |
minimax/minimax-m2.7
sambanova
warming
|
100.00% |
3397 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4129 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:06:44.000Z
|
| — |
qwen/qwen3.8-2.4t-a95b
deepinfra
warming
|
100.00% |
3399 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3399 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:15:46.000Z
|
| — |
google/gemini-3.6-flash
google-vertex
warming
|
100.00% |
3403 ms |
55 tok/s
2 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3403 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:32:31.000Z
|
| — |
qwen/qwen3.5-9b
together
warming
|
100.00% |
3419 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6114 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:27:45.000Z
|
| — |
qwen/qwen2.5-72b-instruct
deepinfra
warming
|
100.00% |
3457 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3457 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:27:46.000Z
|
| — |
deepseek/deepseek-v4-pro
wandb
warming
|
100.00% |
3465 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3465 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:26:52.000Z
|
| — |
mistralai/mistral-nemotron
nvidia-nim
warming
|
100.00% |
3467 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3467 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:37:41.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
engy
warming
|
100.00% |
3471 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3808 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:14:48.000Z
|
| — |
deepseek/deepseek-v4.1-flash
wafer
warming
1 excluded
|
100.00% |
3471 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3975 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- unsupported_route: 1
- Last seen
- 2026-09-16T19:37:17.000Z
|
| — |
z-ai/glm-5.3-flash
featherless
warming
|
100.00% |
3474 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3474 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:52:50.000Z
|
| — |
nvidia/nemotron-3.5-lightning-30b-a3b
nvidia-nim
warming
|
100.00% |
3475 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 13978 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:40:57.000Z
|
| — |
qwen/qwen3.8-27b
cloudflare-workers-ai
warming
|
100.00% |
3475 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3475 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:03:05.000Z
|
| — |
deepseek/deepseek-r1-distill-qwen-32b
cloudflare-workers-ai
warming
|
100.00% |
3491 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3653 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:55:13.000Z
|
| — |
google/gemma-4-26b-a4b-it
makora
warming
|
100.00% |
3504 ms |
Not measured
0 samples, warming |
77 with TTFT |
More
- Provider availability
- 100.00% (7 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7514 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:06:48.000Z
|
| — |
google/gemini-3.1-pro-preview
lightning
warming
|
100.00% |
3506 ms |
41 tok/s
2 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3506 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:40:53.000Z
|
| — |
z-ai/glm-5.3
makora
warming
|
100.00% |
3515 ms |
Not measured
0 samples, warming |
66 with TTFT |
More
- Provider availability
- 100.00% (6 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 10211 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:37:58.000Z
|
| — |
bytedance/doubao-seed-evolving
atlas-cloud
warming
|
100.00% |
3534 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3534 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:18:52.000Z
|
| — |
z-ai/glm-5.3-flash
wafer
warming
|
100.00% |
3540 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3777 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:41:16.000Z
|
| — |
thinkingmachines/inkling-1m
baseten
warming
|
100.00% |
3541 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3541 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:34:55.000Z
|
| — |
moonshotai/kimi-k2.7-code
io-net
warming
|
100.00% |
3546 ms |
116 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3546 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:39:39.000Z
|
| — |
google/gemma-4-31b-it
tinfoil
warming
|
100.00% |
3559 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3701 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:27:48.000Z
|
| — |
deepseek/deepseek-v4-flash-0731
baseten
warming
|
100.00% |
3564 ms |
125 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3827 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:32:29.000Z
|
| — |
z-ai/glm-5.2
featherless
warming
|
100.00% |
3572 ms |
64 tok/s
2 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5532 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:22:40.000Z
|
| — |
google/gemini-3.6-flash
google-ai-studio
warming
|
100.00% |
3577 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3577 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:33:50.000Z
|
| — |
z-ai/glm-4.6
io-net
warming
|
100.00% |
3580 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3580 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:36:54.000Z
|
| — |
moonshotai/kimi-k3
sail-research
warming
|
100.00% |
3581 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3767 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:17:20.000Z
|
| — |
qwen/qwen-vl-ocr-2025-11-20
alibaba
warming
|
100.00% |
3586 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3586 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:11:27.000Z
|
| — |
qwen/qwen3-coder-next
parasail
warming
|
100.00% |
3588 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3588 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:05:26.000Z
|
| — |
meta-llama/llama-3.1-8b-instruct
telnyx
warming
|
100.00% |
3589 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3589 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:05:01.000Z
|
| — |
moonshotai/kimi-k2.5
io-net
warming
|
100.00% |
3593 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4120 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:27:55.000Z
|
| — |
qwen/qwen3.7-max
atlas-cloud
warming
|
100.00% |
3597 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4013 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:27:41.000Z
|
| — |
z-ai/glm-5.1
featherless
warming
|
100.00% |
3600 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 10587 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:50:24.000Z
|
| — |
google/gemma-4-31b-it
novita
warming
|
100.00% |
3605 ms |
56 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3605 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:22:17.000Z
|
| — |
xiaomi/mimo-v2.5
xiaomi
warming
|
100.00% |
3606 ms |
Not measured
0 samples, warming |
99 with TTFT |
More
- Provider availability
- 100.00% (9 samples)
- Within deadline
- 88.89%
- Capacity accepted
- 100.00%
- p95 TTFT
- 24811 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:25:03.000Z
|
| — |
cohere/command-a
azure
warming
|
100.00% |
3620 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3943 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:18:45.000Z
|
| — |
moonshotai/kimi-k2.7-code-highspeed
kimi
warming
|
100.00% |
3620 ms |
Not measured
0 samples, warming |
88 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 14133 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:59:29.000Z
|
| — |
openai/gpt-5.2
openai
warming
|
100.00% |
3627 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3627 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:47:36.000Z
|
| — |
x-ai/grok-4.1-fast-non-reasoning
azure
warming
|
100.00% |
3655 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3655 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:57:46.000Z
|
| — |
z-ai/glm-5.3
nebius
warming
|
100.00% |
3677 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3677 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:31:40.000Z
|
| — |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
nvidia-nim
warming
|
50.00% |
3680 ms |
Not measured
0 samples, warming |
21 with TTFT |
More
- Provider availability
- 50.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3680 ms
- Failure owner
- provider: 1
- Errors
- empty_stream: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:36:45.000Z
|
| — |
xiaomi/mimo-v2.5
deepinfra
warming
|
100.00% |
3683 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3683 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:33:44.000Z
|
| — |
z-ai/glm-5.3-flash
baseten
warming
|
100.00% |
3685 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3734 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:38:30.000Z
|
| — |
moonshotai/kimi-k2-6
venice
warming
|
100.00% |
3699 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3699 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:57:51.000Z
|
| — |
anthropic/claude-fable-5
anthropic
warming
|
100.00% |
3703 ms |
Not measured
0 samples, warming |
86 with TTFT |
More
- Provider availability
- 100.00% (8 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5594 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:33:46.000Z
|
| — |
x-ai/grok-4.20
grok
warming
|
100.00% |
3715 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3869 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:55:52.000Z
|
| — |
moonshotai/kimi-k2.6
azure
warming
|
100.00% |
3717 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4234 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:57:39.000Z
|
| — |
openai/gpt-4.1
lightning
warming
|
100.00% |
3726 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3778 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:51:08.000Z
|
| — |
qwen/qwen3-coder-480b-a35b-instruct-turbo
deepinfra
warming
|
100.00% |
3732 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3732 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:17:06.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
tinfoil
warming
|
100.00% |
3736 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4178 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:13:04.000Z
|
| — |
openai/gpt-5.4-mini
openai
warming
|
100.00% |
3737 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3737 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:38:28.000Z
|
| — |
minimax/minimax-m25
venice
warming
|
100.00% |
3746 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3746 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:01:43.000Z
|
| — |
deepseek/deepseek-v4-pro
featherless
warming
|
100.00% |
3769 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3769 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:04:36.000Z
|
| — |
thinkingmachines/inkling
together
warming
|
100.00% |
3795 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4346 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:57:47.000Z
|
| — |
meta-llama/llama-3.1-8b-instruct
databricks
warming
|
100.00% |
3797 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4121 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:57:49.000Z
|
| — |
anthropic/claude-opus-4.5
anthropic
warming
|
100.00% |
3805 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3805 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T19:18:42.000Z
|
| — |
z-ai/glm-5.3-flash
inceptron
warming
|
100.00% |
3808 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 12041 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:59:41.000Z
|
| — |
z-ai/glm-5.2
parasail
warming
|
100.00% |
3814 ms |
135 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3814 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:12:42.000Z
|
| — |
z-ai/glm-5.1
gmi
warming
|
66.67% |
3851 ms |
Not measured
0 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6688 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:14:13.000Z
|
| — |
zero-g/0gm-1.0-35b-a3b-sia
zero-g
warming
|
100.00% |
3861 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4082 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:27:45.000Z
|
| — |
qwen/qwen3-30b-a3b-fp8
cloudflare-workers-ai
warming
|
100.00% |
3868 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3868 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:28:50.000Z
|
| — |
qwen/qwen3.5-35b-a3b
parasail
warming
|
100.00% |
3894 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6712 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:29:15.000Z
|
| — |
openai/gpt-oss-20b
akashml
warming
|
100.00% |
3895 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5306 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:12:52.000Z
|
| — |
z-ai/glm-5
venice
warming
|
100.00% |
3899 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3899 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:00:53.000Z
|
| — |
google/gemma-4-31b-it
wandb
warming
|
100.00% |
3910 ms |
50 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3910 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:32:00.000Z
|
| — |
qwen/qwen3.5-35b-a3b
atlas-cloud
warming
|
100.00% |
3910 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3910 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T13:36:49.000Z
|
| — |
z-ai/glm-5.3-flash
arcee
warming
|
100.00% |
3924 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4877 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:12:43.000Z
|
| — |
google/gemini-3.1-pro-preview
google-vertex
warming
|
100.00% |
3943 ms |
59 tok/s
2 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4911 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:21:47.000Z
|
| — |
xiaomi/mimo-v2.5
io-net
warming
|
100.00% |
3950 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3950 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:05:39.000Z
|
| — |
deepseek/deepseek-v4-pro-0423
parasail
warming
|
100.00% |
3956 ms |
58 tok/s
2 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3956 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:03:04.000Z
|
| — |
openai/o3
openai
warming
|
100.00% |
3961 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3961 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:47:17.000Z
|
| — |
moonshotai/kimi-k3
featherless
warming
|
100.00% |
3984 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 3984 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:23:23.000Z
|
| — |
qwen/qwen3-vl-235b-a22b-thinking
atlas-cloud
warming
|
100.00% |
4031 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4031 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:49:28.000Z
|
| — |
qwen/qwen3.5-35b-a3b
wandb
warming
|
100.00% |
4048 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4048 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:03:55.000Z
|
| — |
meta-llama/llama-3.3-70b-instruct
parasail
warming
|
100.00% |
4060 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 28102 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:07:07.000Z
|
| — |
openai/gpt-oss-20b
siliconflow
warming
|
100.00% |
4093 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4093 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:27:48.000Z
|
| — |
google/gemini-3.7-flash
google-ai-studio
warming
|
100.00% |
4107 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4107 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:29:12.000Z
|
| — |
z-ai/glm-5
gmi
warming
|
100.00% |
4137 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8624 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:53.000Z
|
| — |
moonshotai/kimi-k3
together
warming
|
100.00% |
4180 ms |
61 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4977 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:32:03.000Z
|
| — |
openai/gpt-oss-120b
akashml
warming
|
100.00% |
4208 ms |
58 tok/s
1 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4737 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:46:51.000Z
|
| — |
z-ai/glm-5.2
regolo
warming
|
100.00% |
4235 ms |
47 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4235 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:37:04.000Z
|
| — |
thinkingmachines/inkling-small
arcee
warming
|
100.00% |
4247 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6219 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:39:45.000Z
|
| — |
openai/gpt-oss-120b
parasail
warming
|
100.00% |
4333 ms |
106 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4333 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:12:56.000Z
|
| — |
deepseek/deepseek-v4-pro
arcee
warming
|
100.00% |
4352 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4857 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:29:02.000Z
|
| — |
zai-org/GLM-5.1
nebius
warming
|
100.00% |
4360 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5151 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:14:13.000Z
|
| — |
z-ai/glm-5.3-flash
pearl
warming
|
100.00% |
4407 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 12409 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:30:53.000Z
|
| — |
z-ai/glm-4.7-flash
io-net
warming
|
100.00% |
4432 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9464 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:03:10.000Z
|
| — |
tencent/hy4-preview
gmi
warming
|
100.00% |
4448 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4897 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:02:53.000Z
|
| — |
google/gemini-3.8-flash
google-ai-studio
warming
|
100.00% |
4502 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4502 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:52:53.000Z
|
| — |
minimax/minimax-m2.5
atlas-cloud
warming
|
100.00% |
4503 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4503 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:03:29.000Z
|
| — |
x-ai/grok-4.1-fast-reasoning
azure
warming
|
100.00% |
4529 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5045 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:57:46.000Z
|
| — |
openai/o4-mini
openai
warming
|
100.00% |
4575 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4575 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:42:38.000Z
|
| — |
z-ai/glm-4.7
venice
warming
|
100.00% |
4606 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7846 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:08:02.359Z
|
| — |
z-ai/glm-5.2
arcee
warming
|
100.00% |
4646 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9554 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:03:54.000Z
|
| — |
zai-org/glm-4.7-flash
novita
warming
|
50.00% |
4669 ms |
Not measured
0 samples, warming |
21 with TTFT |
More
- Provider availability
- 50.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4669 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:37:28.000Z
|
| — |
bytedance/doubao-seed-2.1-turbo-260628
atlas-cloud
warming
|
100.00% |
4671 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6374 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:33:42.000Z
|
| — |
moonshotai/kimi-k3
atlas-cloud
warming
|
100.00% |
4752 ms |
87 tok/s
1 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5125 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:12:39.000Z
|
| — |
moonshotai/kimi-k2.6
inceptron
warming
|
100.00% |
4767 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 13818 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:39:35.000Z
|
| — |
z-ai/glm-5v-turbo
zai
warming
|
100.00% |
4815 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 27600 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:31:12.000Z
|
| — |
qwen/qwen3.6-35b-a3b
scaleway
warming
|
100.00% |
4847 ms |
Not measured
0 samples, warming |
44 with TTFT |
More
- Provider availability
- 100.00% (4 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4974 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:14:58.000Z
|
| — |
deepseek/deepseek-ocr
atlas-cloud
warming
|
100.00% |
4985 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 4985 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:29:58.000Z
|
| — |
minimax/minimax-m2.7
morph
warming
|
25.00% |
5046 ms |
Not measured
0 samples, warming |
41 with TTFT |
More
- Provider availability
- 25.00% (4 samples)
- Within deadline
- 25.00%
- Capacity accepted
- 50.00%
- p95 TTFT
- 5046 ms
- Failure owner
- provider: 3
- Errors
- empty_stream: 1, provider_error: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:51.000Z
|
| — |
qwen/qwen3.8-2.4t-a95b
siliconflow
warming
|
100.00% |
5079 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5079 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:54:49.000Z
|
| — |
qwen/qwen3-vl-235b-a22b-instruct
parasail
warming
|
100.00% |
5114 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5114 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:21:47.000Z
|
| — |
minimax/minimax-m27
venice
warming
|
100.00% |
5303 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5303 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T18:42:53.000Z
|
| — |
moonshotai/kimi-k2.7-code
featherless
warming
|
100.00% |
5444 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5909 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:21:49.000Z
|
| — |
mistralai/mistral-nemo
chutes
warming
|
100.00% |
5579 ms |
Not measured
0 samples, warming |
32 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8587 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:46:40.000Z
|
| — |
moonshotai/kimi-k3
siliconflow
warming
|
100.00% |
5598 ms |
51 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5598 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:22:47.000Z
|
| — |
moonshotai/kimi-k2.6
featherless
warming
|
100.00% |
5612 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5612 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:32:07.000Z
|
| — |
moonshotai/kimi-k3
makora
warming
|
100.00% |
5643 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 66.67%
- Capacity accepted
- 100.00%
- p95 TTFT
- 24705 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:59:18.000Z
|
| — |
moonshotai/kimi-k2.6
wandb
warming
|
100.00% |
5803 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5803 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:42:08.000Z
|
| — |
qwen/qwen-vl-ocr
alibaba
warming
|
100.00% |
5898 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 5898 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:38:22.000Z
|
| — |
z-ai/glm-5.3-flash
friendli
warming
|
71.43% |
6057 ms |
Not measured
0 samples, warming |
75 with TTFT |
More
- Provider availability
- 71.43% (7 samples)
- Within deadline
- 71.43%
- Capacity accepted
- 71.43%
- p95 TTFT
- 7178 ms
- Failure owner
- provider: 2
- Errors
- provider_error: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:53:18.000Z
|
| — |
Qwen/Qwen3-235B-A22B-Instruct-2507
nebius
warming
|
100.00% |
6774 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 6774 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:34:54.000Z
|
| — |
minimax/minimax-m2.7
featherless
warming
|
100.00% |
7024 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8456 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:36:47.000Z
|
| — |
moonshotai/kimi-k3
arcee
warming
|
100.00% |
7156 ms |
45 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7156 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:27:30.000Z
|
| — |
xiaomimimo/mimo-v2.5
novita
warming
|
100.00% |
7435 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7435 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:18:55.000Z
|
| — |
qwen/qwen3.5-397b-a17b
morph
warming
1 excluded
|
33.33% |
7439 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 33.33% (3 samples)
- Within deadline
- 33.33%
- Capacity accepted
- 33.33%
- p95 TTFT
- 7439 ms
- Failure owner
- provider: 2
- Errors
- provider_error: 2
- Excluded from provider availability
- provider_error: 1
- Last seen
- 2026-09-17T06:12:44.000Z
|
| — |
z-ai/glm-5.2
chutes
warming
|
100.00% |
7506 ms |
11 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 8710 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:25:11.000Z
|
| — |
google/gemma-4-31b-turbo
chutes
warming
|
100.00% |
7654 ms |
Not measured
0 samples, warming |
55 with TTFT |
More
- Provider availability
- 100.00% (5 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 15819 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:20:19.000Z
|
| — |
z-ai/glm-5.1
chutes
warming
|
33.33% |
7776 ms |
Not measured
0 samples, warming |
31 with TTFT |
More
- Provider availability
- 33.33% (3 samples)
- Within deadline
- 33.33%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7776 ms
- Failure owner
- provider: 2
- Errors
- TimeoutError: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:48:11.000Z
|
| — |
z-ai/glm-5.1
zai
warming
|
100.00% |
7937 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 7937 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T12:43:51.000Z
|
| — |
z-ai/glm-4.7
zai
warming
|
100.00% |
8479 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 14968 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:36:58.000Z
|
| — |
qwen/qwen3-32b
chutes
warming
|
100.00% |
8569 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11186 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:09:58.000Z
|
| — |
moonshotai/kimi-k2.6
chutes
warming
|
100.00% |
8712 ms |
7 tok/s
1 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 11478 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:37:59.000Z
|
| — |
qwen/qwen3.5-397b-a17b
chutes
warming
|
100.00% |
8723 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 13714 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:56:28.000Z
|
| — |
z-ai/glm-4.5
zai
warming
|
100.00% |
9095 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 12079 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:40:52.000Z
|
| — |
deepseek/deepseek-v3
deepinfra
warming
|
100.00% |
9162 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 9162 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:51:48.000Z
|
| — |
z-ai/glm-4.7
mancer
warming
|
100.00% |
11714 ms |
Not measured
0 samples, warming |
22 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- 50.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 20891 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:30:59.000Z
|
| — |
deepseek/deepseek-v3.2
chutes
warming
|
100.00% |
13991 ms |
Not measured
0 samples, warming |
33 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 16836 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:40:36.000Z
|
| — |
Qwen/Qwen3-30B-A3B-Instruct-2507
nebius
warming
|
100.00% |
14035 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 14035 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T16:57:52.000Z
|
| — |
qwen/qwen3.8-flash-next
featherless
warming
|
100.00% |
14248 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 14248 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:16:05.000Z
|
| — |
z-ai/glm-5.3-p
novita
warming
|
100.00% |
17012 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 17012 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:19:00.000Z
|
| — |
z-ai/glm-5.3-flash
nebius
warming
|
100.00% |
17147 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 17147 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:21:59.000Z
|
| — |
google/gemini-3.5-flash
atlas-cloud
warming
|
66.67% |
17192 ms |
57 tok/s
1 samples, warming |
32 with TTFT |
More
- Provider availability
- 66.67% (3 samples)
- Within deadline
- 33.33%
- Capacity accepted
- 100.00%
- p95 TTFT
- 21064 ms
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:16:47.000Z
|
| — |
qwen/qwen3.6-35b-a3b
featherless
warming
|
100.00% |
19280 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 100.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 19280 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:04:06.000Z
|
| — |
qwen/qwen3.6-27b
chutes
warming
|
100.00% |
20321 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 20321 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:55:08.000Z
|
| — |
openai/gpt-oss-120b
novita
warming
|
100.00% |
22168 ms |
54 tok/s
1 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 22168 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:07:25.000Z
|
| — |
qwen/qwen3.6-27b
featherless
warming
|
100.00% |
26890 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 26890 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:11:58.000Z
|
| — |
xiaomi/mimo-v2.5-pro
deepinfra
warming
|
100.00% |
29446 ms |
Not measured
0 samples, warming |
11 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- 29446 ms
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:32:39.000Z
|
| — |
Sao10K/L3-8B-Stheno-v3.2
novita
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:05:53.118Z
|
| — |
anthropic/claude-haiku-4.5
anthropic
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:54:17.757Z
|
| — |
deepseek/deepseek-ocr-2
novita
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 100.00% (2 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:57:50.825Z
|
| — |
deepseek/deepseek-v4-pro
deepinfra
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
30 with TTFT |
More
- Provider availability
- 100.00% (3 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:04:46.703Z
|
| — |
google/gemma-4-12b-it
siliconflow
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
420 with TTFT |
More
- Provider availability
- 100.00% (42 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:45:44.300Z
|
| — |
meta-llama/meta-llama-3.1-8b-instruct-turbo
deepinfra
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:57:26.073Z
|
| — |
neurometric/tool-choice
neurometric
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
5000 with TTFT |
More
- Provider availability
- 100.00% (500 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:26:25.402Z
|
| — |
openai/gpt-4.1
openai
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
560 with TTFT |
More
- Provider availability
- 100.00% (56 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T17:58:51.460Z
|
| — |
openai/gpt-5-nano
openai
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
340 with TTFT |
More
- Provider availability
- 100.00% (34 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:07:57.544Z
|
| — |
openai/text-embedding-3-large
openai
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
1480 with TTFT |
More
- Provider availability
- 100.00% (148 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T08:44:50.597Z
|
| — |
qwen/qwen3.7-flash
alibaba
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:42:52.660Z
|
| — |
sao10k/l3-8b-lunaris
novita
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:06:57.818Z
|
| — |
sao10k/l3-8b-lunaris-v1-turbo
deepinfra
warming
|
100.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 100.00% (1 samples)
- Within deadline
- Not measured
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:04:47.762Z
|
| — |
moonshotai/kimi-k3
baseten
warming
|
97.89% |
Not measured |
85 tok/s
2 samples, warming |
950 with TTFT |
More
- Provider availability
- 97.89% (95 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 2
- Errors
- empty_output: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:27:34.000Z
|
| — |
baidu/cobuddy
novita
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 0.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:07:11.000Z
|
| — |
baidu/ernie-4.5-21B-a3b
novita
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 0.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:49:48.000Z
|
| — |
deepseek/deepseek-v4-flash
alibaba
warming
|
Not measured |
Not measured |
103 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:56:29.000Z
|
| — |
deepseek/deepseek-v4-flash
atlas-cloud
warming
|
Not measured |
Not measured |
119 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:06:01.000Z
|
| — |
deepseek/deepseek-v4-flash
novita
warming
|
Not measured |
Not measured |
137 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:36:22.000Z
|
| — |
deepseek/deepseek-v4-pro
parasail
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 0.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:00:51.000Z
|
| — |
deepseek/deepseek-v4-pro-0423
deepinfra
warming
|
Not measured |
Not measured |
10 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:53:36.000Z
|
| — |
deepseek/deepseek-v4-pro-0423
siliconflow
warming
|
Not measured |
Not measured |
68 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:47:57.000Z
|
| — |
deepseek/deepseek-v4-pro-0423
venice
warming
|
Not measured |
Not measured |
18 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:58:31.000Z
|
| — |
google/gemini-2.5-flash-lite
atlas-cloud
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:12:55.000Z
|
| — |
google/gemini-3.5-flash
lightning
warming
|
Not measured |
Not measured |
82 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T23:12:47.000Z
|
| — |
google/gemma-4-31b-it
nvidia-nim
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 0.00% (2 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 2
- Errors
- TimeoutError: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:54:40.000Z
|
| — |
google/gemma-4-31b-it
parasail
warming
|
Not measured |
Not measured |
46 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T22:26:58.000Z
|
| — |
google/gemma-4-31b-it
siliconflow
warming
|
Not measured |
Not measured |
98 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:56:19.000Z
|
| — |
meta-llama/llama-3.2-90b-vision-instruct
nvidia-nim
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
30 with TTFT |
More
- Provider availability
- 0.00% (3 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 3
- Errors
- TimeoutError: 3
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:52:05.000Z
|
| — |
mindai/macaron-v1-tall
novita
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- empty_stream: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T14:54:41.000Z
|
| — |
minimax/minimax-m2.5
inceptron
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
40 with TTFT |
More
- Provider availability
- 0.00% (4 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 4
- Errors
- provider_error: 4
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:39:37.000Z
|
| — |
minimax/minimax-m3
atlas-cloud
warming
|
Not measured |
Not measured |
175 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:17:06.000Z
|
| — |
minimax/minimax-m3
deepinfra
warming
|
Not measured |
Not measured |
9 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:48:05.000Z
|
| — |
minimax/minimax-m3
morph
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
30 with TTFT |
More
- Provider availability
- 0.00% (3 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 66.67%
- p95 TTFT
- Not measured
- Failure owner
- provider: 3
- Errors
- empty_stream: 2, provider_error: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:27:27.000Z
|
| — |
minimax/minimax-m3
telnyx
warming
|
Not measured |
Not measured |
112 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:12:29.000Z
|
| — |
minimax/minimax-m3
wandb
warming
|
Not measured |
Not measured |
179 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:07:02.000Z
|
| — |
minimax/minimax-m3-preview
venice
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:16:09.000Z
|
| — |
moonshotai/kimi-k2-7-code
venice
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
10 with TTFT |
More
- Provider availability
- 0.00% (1 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 1
- Errors
- TimeoutError: 1
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T15:18:01.000Z
|
| — |
moonshotai/kimi-k2.6
atlas-cloud
warming
|
Not measured |
Not measured |
54 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:57:15.000Z
|
| — |
moonshotai/kimi-k2.6
fireworks
warming
|
Not measured |
Not measured |
70 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T00:46:31.000Z
|
| — |
moonshotai/kimi-k2.6
io-net
warming
|
Not measured |
Not measured |
40 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T01:46:44.000Z
|
| — |
moonshotai/kimi-k2.7-code
alibaba
warming
|
Not measured |
Not measured |
42 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T21:32:39.000Z
|
| — |
moonshotai/kimi-k3
cloudflare-workers-ai
warming
|
Not measured |
Not measured |
24 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-16T20:38:35.000Z
|
| — |
moonshotai/kimi-k3
deepinfra
warming
|
Not measured |
Not measured |
40 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:26:04.000Z
|
| — |
moonshotai/kimi-k3
nvidia-nim
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
30 with TTFT |
More
- Provider availability
- 0.00% (3 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 3
- Errors
- TimeoutError: 3
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:15:24.000Z
|
| — |
moonshotai/kimi-k3
venice
warming
|
Not measured |
Not measured |
75 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:36:54.000Z
|
| — |
openai/gpt-oss-120b
cloudflare-workers-ai
warming
|
Not measured |
Not measured |
115 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T03:47:08.000Z
|
| — |
openai/gpt-oss-120b
deepinfra
warming
|
Not measured |
Not measured |
57 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T02:37:25.000Z
|
| — |
qwen/qwen3-235b-a22b-thinking-2507
chutes
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 0.00% (2 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 2
- Errors
- provider_error: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:12:21.000Z
|
| — |
qwen/qwen3-next-80b-a3b-instruct
databricks
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
30 with TTFT |
More
- Provider availability
- 0.00% (3 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 3
- Errors
- TimeoutError: 3
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T11:13:15.000Z
|
| — |
qwen/qwen3.6-27b
morph
warming
2 excluded
|
0.00% |
Not measured |
Not measured
0 samples, warming |
40 with TTFT |
More
- Provider availability
- 0.00% (4 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 75.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 4
- Errors
- TimeoutError: 1, empty_stream: 2, provider_error: 1
- Excluded from provider availability
- provider_error: 2
- Last seen
- 2026-09-17T04:46:50.000Z
|
| — |
xiaomi/mimo-v2.5-pro
atlas-cloud
warming
1 excluded
|
Not measured |
Not measured |
40 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- probe_config_error: 1
- Last seen
- 2026-09-17T11:37:36.000Z
|
| — |
z-ai/glm-5.2
alibaba
warming
|
Not measured |
Not measured |
34 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T04:51:46.000Z
|
| — |
z-ai/glm-5.2
deepinfra
warming
|
Not measured |
Not measured |
46 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T05:52:31.000Z
|
| — |
z-ai/glm-5.2
io-net
warming
|
Not measured |
Not measured |
151 tok/s
2 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T06:57:35.000Z
|
| — |
z-ai/glm-5.2
siliconflow
warming
|
Not measured |
Not measured |
56 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:11:42.000Z
|
| — |
z-ai/glm-5.2
telnyx
warming
|
Not measured |
Not measured |
58 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T09:27:11.000Z
|
| — |
z-ai/glm-5.2
zai
warming
|
Not measured |
Not measured |
77 tok/s
1 samples, warming |
00 with TTFT |
More
- Provider availability
- Not measured (0 samples)
- Within deadline
- Not measured
- Capacity accepted
- Not measured
- p95 TTFT
- Not measured
- Failure owner
- None
- Errors
- None
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:11:51.000Z
|
| — |
z-ai/glm-5.3
phala
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
110 with TTFT |
More
- Provider availability
- 0.00% (11 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 11
- Errors
- provider_error: 11
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:24:41.000Z
|
| — |
z-ai/glm-5.3-flash
near-ai
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
250 with TTFT |
More
- Provider availability
- 0.00% (25 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 25
- Errors
- provider_error: 25
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T12:24:43.000Z
|
| — |
z-ai/glm-5.3-flash
nvidia-nim
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 0.00% (2 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 2
- Errors
- TimeoutError: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T07:13:29.000Z
|
| — |
z-ai/glm-5.3-flash
phala
warming
|
0.00% |
Not measured |
Not measured
0 samples, warming |
20 with TTFT |
More
- Provider availability
- 0.00% (2 samples)
- Within deadline
- 0.00%
- Capacity accepted
- 100.00%
- p95 TTFT
- Not measured
- Failure owner
- provider: 2
- Errors
- provider_error: 2
- Excluded from provider availability
- None
- Last seen
- 2026-09-17T10:51:44.000Z
|