OpenAI compatible API · Attested · Public status
Cerebras
Explore Cerebras models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Cerebrascerebras
No logs
| Provider | Cerebras |
|---|---|
| Provider website | https://www.cerebras.ai/ |
| Models | 6 public models |
| Prepaid routes | 6 |
| BYOK routes | 6 |
| Zero data retention | yes |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Tracked as provider-ZDR. Cerebras documents zero-retention inference and ZDR-compliant ephemeral prompt caching that is never persisted. Policy source |
Measured performance
60 samplesContinuously sampled across Cerebras's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1045 ms |
|---|---|
| Effective throughput | 151 tok/s n=6 |
| Uptime | 90.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 1045 ms | 1045 ms | 151 tok/s n=2 | 100.00% | — | 7 |
| cerebras/gpt-oss-120b | 1426 ms | 1369 ms | 431 tok/s n=2 | 100.00% | — | 13 |
| google/gemma-4-31b-it | 2226 ms | 2226 ms | 27 tok/s n=1 | 88.89% | — | 9 |
| z-ai/glm-4.7 | 951 ms | 951 ms | — | 84.62% | — | 13 |
| cerebras/zai-glm-4.7 | 970 ms | 970 ms | 38 tok/s n=1 | 83.33% | 4 provider_error |
12 |
| cerebras/gemma-4-31b | 2116 ms | 2116 ms | — | 83.33% | — | 6 |
Cerebras performance history · Full provider & model leaderboard.
Provider models
Models served by Cerebras.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
cerebras/gemma-4-31bGemma 4 31B |
IQ 101#66 | 131,072 | 2 | $1.0395/1M | $1.5645/1M | prepaid BYOK |
cerebras/gpt-oss-120bOpenAI GPT OSS |
IQ 105#53 | 131,072 | 2 | $0.3675/1M | $0.7875/1M | prepaid BYOK |
cerebras/zai-glm-4.7Z.ai GLM 4.7 |
— | 131,072 | 2 | $2.3625/1M | $2.8875/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#66 | 262,144 | 2 | $1.0395/1M | $1.5645/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#53 | 131,072 | 2 | $0.3675/1M | $0.7875/1M | prepaid BYOK |
z-ai/glm-4.7Z.ai: GLM 4.7 |
IQ 103#59 | 204,800 | 2 | $2.3625/1M | $2.8875/1M | prepaid BYOK |