Cerebras
Inference providerUS Westprices checked Oct 23, 06:00 UTC
Cerebras serves 2 models at a verified price. On the 2 it shares with other hosts, it is never the cheapest and charges a median 302% above it.
Models served22 with open weights · +1 without a price
Cheapest input, per M$0.35gpt-oss-120b
Uptime, last 24 h99.7%average of its 1 OpenRouter endpoint
Sign-upCard requiredno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| Qwen3.8 27B | fp16/fp8 | 128K | — | $0.99 | $1.49 | — |
| Gemma 4 31Bno verified price | — | 128K | — | — | — | — |
| gpt-oss-120b | fp16/8 | 128K | ✓ | $0.35 | $0.75 | $0.35 |
3 of 3 models · prices per million tokens · precision and context: read at Cerebras's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Cerebras declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Card required | inference-docs.cerebras.ai |
| Free credits | None stated | — |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | cerebras.ai |
| API documentation | Its own docs | inference-docs.cerebras.ai |
| Status page | Outages and incidents, as Cerebras reports them | status.cerebras.ai |
| Terms of service | Its terms | cerebras.ai |
| Free credits | $5 promotional credit | cerebras.ai |
Links checked Oct 8.