OpenAI compatible API · Attested · Public status
Together performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Together.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
together
37 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1854 ms |
|---|---|
| p95 TTFT | 9257 ms |
| p50 TTFB | 1987 ms |
| Effective throughput | 61 tok/s n=11 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 697 ms | 697 ms | 129 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1000 ms | 1000 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-3-ultra-550b-a55b | 1515 ms | 1515 ms | 124 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1696 ms | 1696 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k3 | 1707 ms | 1707 ms | 39 tok/s n=2 | 100.00% | — | 3 |
| openai/gpt-oss-20b | 1854 ms | 1854 ms | — | 100.00% | — | 6 |
| qwen/qwen-2.5-7b-instruct | 1868 ms | 1868 ms | — | 100.00% | — | 4 |
| thinkingmachines/inkling | 1987 ms | 1987 ms | 24 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.2 | 2263 ms | 2263 ms | — | 100.00% | — | 7 |
| google/gemma-3n-e4b-it | 2342 ms | 2342 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 2412 ms | 2412 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-pro | — | — | 69 tok/s n=2 | — | 7 probe_config_error |
0 |
| google/gemma-4-31b-it | — | — | 53 tok/s n=2 | — | 1 probe_config_error |
0 |
| minimax/minimax-m3 | — | — | 61 tok/s n=2 | — | 7 probe_config_error |
0 |