OpenAI compatible API. Attested gateway. Public status.
Cerebras
Cerebras models on TrustedRouter with prices, routes, policy notes, and source links.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
cerebras
No logs
| Provider | Cerebras |
|---|---|
| Models | 8 public models |
| Prepaid routes | 4 |
| BYOK routes | 8 |
| Zero data retention | yes |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Tracked as provider-ZDR. Cerebras documents ZDR-compliant ephemeral prompt caching and no persisted prompt cache data. Policy source |
Measured performance
259 samplesContinuously sampled across Cerebras's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 6138 ms |
|---|---|
| Throughput | — |
| Uptime | 98.07% |
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| cerebras/zai-glm-4.7 | 4770 ms | 4769 ms | — | 97.14% | — | 70 |
| openai/gpt-oss-120b | 6138 ms | 6138 ms | — | 98.33% | — | 60 |
| cerebras/gpt-oss-120b | 6368 ms | 6367 ms | — | 100.00% | — | 61 |
| z-ai/glm-4.7 | 7452 ms | 7452 ms | — | 97.06% | — | 68 |
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/gpt-oss-120bCerebras GPT OSS 120B |
IQ 95#59 | 131,072 | 2 | $0.385/1M | $0.825/1M | prepaid BYOK |
cerebras/zai-glm-4.7Cerebras Z.AI GLM 4.7 |
— | 202,752 | 2 | $2.475/1M | $3.025/1M | prepaid BYOK |
meta-llama/llama-3.1-70b-instructMeta: Llama 3.1 70B Instruct |
— | 131,072 | 1 | $0.44/1M | $0.44/1M | BYOK |
meta-llama/llama-3.1-8b-instructMeta: Llama 3.1 8B Instruct |
— | 131,072 | 1 | $0.198/1M | $0.198/1M | BYOK |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 1 | $0.242/1M | $0.55/1M | BYOK |
meta-llama/llama-4-maverickMeta: Llama 4 Maverick |
IQ # | 1,048,576 | 1 | $0.385/1M | $1.1/1M | BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 95#59 | 131,072 | 2 | $0.385/1M | $0.825/1M | prepaid BYOK |
z-ai/glm-4.7Z.ai: GLM 4.7 |
IQ 102#46 | 202,752 | 2 | $2.475/1M | $3.025/1M | prepaid BYOK |