Cerebras Inference
- Categories
- Inference hosts
- Owned by
- Cerebras Systems Inc. (private)
- HQ
- US
- Website
- https://www.cerebras.ai
- Pricing page
- https://inference-docs.cerebras.ai/models/overview
- Fee model
- per_token
- Fees
- Pay-as-you-go per token on public endpoints; Dedicated Endpoints for other model families (contact sales)
- Free tier
- Free trial tier with reduced context (64-65k) and rate limits (e.g. 1M tokens/day)
- OpenAI-compatible API
- yes
- Notes
- Only 2 models on public endpoints. Marketing pricing page shows no numbers; prices from per-model docs pages. Also sold via AWS Marketplace, OpenRouter, Hugging Face, Vercel.
- Sources
- https://inference-docs.cerebras.ai/models/overview https://inference-docs.cerebras.ai/models/openai-oss https://inference-docs.cerebras.ai/models/qwen-3.8-27b collected 2026-09-18
LLM prices (2 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| gpt-oss-120b gpt-oss-120b |
$0.35 | $0.75 | — | 131k | ✓ src |
| Qwen3.8-27B qwen-3.8-27b |
$0.99 | $1.49 | — | 131k | ✓ src |