OpenAI compatible API · Attested · Public status

Baseten performance

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Baseten.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

baseten

63 samples

Provider overview

Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.

p50 TTFT1668 ms
p95 TTFT3969 ms
p50 TTFB2168 ms
Effective throughput71 tok/s n=12
Uptime93.65%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
moonshotai/kimi-k3 1252 ms 1252 ms 47 tok/s n=1 100.00% 8
thinkingmachines/inkling-1m 1284 ms 1284 ms 64 tok/s n=1 100.00% 5
thinkingmachines/inkling-small 1484 ms 1484 ms 69 tok/s n=1 100.00% 5
openai/gpt-oss-120b 1590 ms 1590 ms 121 tok/s n=1 100.00% 3
z-ai/glm-4.7 1668 ms 1668 ms 100.00% 7
deepseek/deepseek-v4-pro 2016 ms 2016 ms 72 tok/s n=2 100.00% 6
z-ai/glm-5.2 2912 ms 2912 ms 45 tok/s n=2 100.00% 5
nvidia/nemotron-3-ultra-550b-a55b 3087 ms 3087 ms 234 tok/s n=1 100.00% 4
z-ai/glm-5.2-fast 3179 ms 3179 ms 64 tok/s n=1 100.00% 7
moonshotai/kimi-k2.6 3440 ms 3440 ms 97 tok/s n=1 87.50% 8
moonshotai/kimi-k2.7-code 567 ms 567 ms 74 tok/s n=1 40.00% 5
Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

By signing in you agree to the terms of service and privacy policy.