OpenAI compatible API · Attested · Public status

Fireworks AI performance

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

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

fireworks

64 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 TTFT1321 ms
p95 TTFT10865 ms
p50 TTFB1551 ms
Effective throughput58 tok/s n=14
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
moonshotai/kimi-k2.7-code 666 ms 666 ms 59 tok/s n=1 100.00% 4
z-ai/glm-5.2-fast 730 ms 729 ms 100 tok/s n=2 100.00% 5
deepseek/deepseek-v4-pro 952 ms 952 ms 57 tok/s n=1 100.00% 6
openai/gpt-oss-20b 1060 ms 1059 ms 100.00% 8
openai/gpt-oss-120b 1308 ms 1308 ms 151 tok/s n=2 100.00% 4
deepseek/deepseek-v4-flash 1321 ms 1321 ms 153 tok/s n=1 100.00% 8
moonshotai/kimi-k2.6 1562 ms 1562 ms 31 tok/s n=2 100.00% 7
z-ai/glm-5.2 2007 ms 2007 ms 38 tok/s n=1 100.00% 2
deepseek/deepseek-v4-flash-0731 2845 ms 2845 ms 57 tok/s n=1 100.00% 7
minimax/minimax-m3 3677 ms 3677 ms 106 tok/s n=1 100.00% 6
moonshotai/kimi-k3 3928 ms 3927 ms 36 tok/s n=2 100.00% 7
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.