Baltor Get started

Endpoints

Cerebras

A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.

Addresses and facts

Authentication
Authorization: Bearer, with the key in CEREBRAS_API_KEY provider documentation, read
Structured output
provider documentation, read
Tool calling
provider documentation, read
Rate limits
Read the page provider documentation, read
Prices
Read the page provider documentation, read
Data retention
The privacy policy says Cerebras does not retain the inputs and outputs of its inference services, as its section 6 describes. Read the page provider documentation, read
Documentation
Unknown
Output limits Baltor recorded
Unknown

Harness setup

Replace gpt-oss-120b with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "cerebras": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Cerebras",
      "options": {
        "baseURL": "https://api.cerebras.ai/v1",
        "apiKey": "{env:CEREBRAS_API_KEY}"
      },
      "models": {
        "gpt-oss-120b": {
          "name": "gpt-oss-120b"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "cerebras": {
      "baseUrl": "https://api.cerebras.ai/v1",
      "api": "openai-completions",
      "apiKey": "$CEREBRAS_API_KEY",
      "models": [
        {
          "id": "gpt-oss-120b"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Cerebras documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Cerebras documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Models it lists

Prices in US dollars per million tokens, input and output, as models.dev, read records them.

ModelInputOutputContextAs of
GPT OSS 120B gpt-oss-120b0.350 USD0.750 USD131,072 older than 30 days
Qwen3.8 27B qwen-3.8-27b0.990 USD1.49 USD65,536