Integration

Cerebras Inference integration

Cerebras Inference runs open models (such as gpt-oss-120b and qwen-3.8-27b) on Cerebras hardware behind an OpenAI-compatible API. Generate chat completions (with tools, structured JSON outputs and reasoning controls) or plain text completions, list the models your key can use, and read the public model catalog with per-token pricing, capabilities and limits. Streaming responses, the Prometheus metrics endpoint, the Batch and Files APIs (Private Preview, enabled per organization by Cerebras) and the separate Management API for dedicated endpoints (its own management key) are not exposed. Authentication is an API key from the Cerebras Cloud console sent as Authorization: Bearer.

Connect Cerebras Inference How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Cerebras Inference.Built from the 6 Cerebras Inference tools below, on the connection you add once.

What you can do with Cerebras Inference

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Model, 4 operations

get_modelGet modelGETReturns one model available to your API key: its id, owner and creation time.
get_public_modelGet public modelGETReturns one public catalog model with its description, per-token pricing, capabilities, supported parameters, limits and deprecation flags. Needs no API key.
list_modelsList modelsGETLists the models available to your API key, each with its id, owner and creation time (OpenAI-compatible list). Use an id as model in create_chat_completion.
list_public_modelsList public modelsGETLists the public Cerebras model catalog with name, description, per-token pricing, capabilities, supported parameters, context and completion limits and deprecation flags. Needs no API key.

Completion, 2 operations

create_chat_completionCreate chat completionPOSTGenerates the next assistant message for a conversation (roles system, user, assistant, developer, tool), with optional tools, structured JSON output and reasoning controls. Returns the reply in choices[0].message and token usage.
create_completionCreate completionPOSTGenerates a text continuation of a raw prompt (no chat roles) with the given model. Returns the text in choices[0].text and token usage. For conversations prefer create_chat_completion.

Use Cerebras Inference from Claude Code, Cursor or Codex

Connect Cerebras Inference in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Cerebras Inference operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Cerebras Inference

Create your workspace
Sign up free. Nothing to install.
Connect Cerebras Inference once
Add your Cerebras Inference connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.