Integration

Avian integration

Avian runs an OpenAI-compatible LLM inference API for open-weight models such as DeepSeek, MiniMax, GLM, Kimi and MiMo. List the available models with their context length and per-token prices, and send chat completions (with optional function calling) to any of them. Usage is billed per token from a prepaid balance. Streaming, the account balance route and the GPU compute rental are not exposed. Authentication is an Avian API key (it starts with avian-), created in the API Keys section of the dashboard and sent as a Bearer token in the Authorization header.

Connect Avian How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Avian.Built from the 2 Avian tools below, on the connection you add once.

What you can do with Avian

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.

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTCreates a chat completion: send a model and a list of messages, get the reply in choices[0].message.content (or tool_calls) plus token usage. Billed per token from the prepaid balance.

Model, 1 operation

list_modelsList modelsGETLists the models served by Avian with their context length, maximum output, reasoning flag and per-million-token prices. Pass a returned id as model to create_chat_completion.

Use Avian from Claude Code, Cursor or Codex

Connect Avian in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Avian 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 Avian

Create your workspace
Sign up free. Nothing to install.
Connect Avian once
Add your Avian 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.