Cerebras: API key and base URL
Wafer-scale hardware, very high throughput. Bring your own key; nothing is billed by us.
What the harness already knows
| Provider id | cerebras |
| Bundled base URL | https://api.cerebras.ai/v1 |
| Protocol | OpenAI-compatible chat completions |
| API key | CEREBRAS_API_KEY |
| Model discovery | Yes — the model list is asked of the endpoint rather than shipped. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export CEREBRAS_API_KEY="..."Keys are issued by Cerebras — where to get one.
API key setup and troubleshooting
Official setup guide (checked 2026-10-24)
Create a key using the official guide below, then run this command and paste the key into the prompt. OHarness saves it in its credential store. A key set in the process environment takes precedence over a stored key.
oharness auth login cerebrasCEREBRAS_API_KEY is an environment variable, not a top-level config.json field. For an endpoint override, merge the providers block below into ~/.oharness/config.json; preserve your other settings. The base URL must not include /chat/completions.
{
"providers": {
"cerebras": {
"baseUrl": "https://api.cerebras.ai/v1"
}
}
}If the request fails
- 401 or 403: read the response body, check the active key, account access and credit. An old environment variable can override a newly saved key. A terminal export only applies to that shell and processes started from it.
- 404: check the endpoint and the exact model ID in the vendor console. 429: check the provider’s rate limits and quota before retrying. Model names in a bundled snapshot may no longer be available.
Install OHarness · Provider configuration · Configuration files
Models on Cerebras
The newest models Cerebras serves that can call tools, from the models.dev snapshot OHarness ships. The harness also asks the endpoint for its live list, so a model released after this snapshot still appears in the picker.
| Model id | Context / output | $/M in / cached / out | Reasoning |
|---|---|---|---|
qwen-3.8-27b | 66K / 33K | 0.99 / — / 1.49 | Yes |
gpt-oss-120b | 131K / 41K | 0.35 / — / 0.75 | Yes |
List prices in USD per million tokens, read from models.dev on 2026-09-19. Cerebras changes its prices and models; its own pricing page is the authority. Start a session on the newest:
oharness -m cerebras/qwen-3.8-27bWhat you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.