Integration

ImageRouter integration

ImageRouter is one API in front of many image, video and text (LLM) models. Generate images from a prompt or from source images (URLs, data URIs or an uploaded file), generate videos from a prompt or a start image, run OpenAI-compatible chat completions and responses, list and inspect the available models with their prices and supported parameters, and read the account's remaining credits. Every generation and text call is billed to the account's prepaid credits. Not exposed: streaming, the management-key routes that mint, list and delete API keys (they need a separate management key), the key-check route and the older v1 model list. Authentication is an ImageRouter API key (created on imagerouter.io under API keys) sent as a Bearer token.

Connect ImageRouter How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ImageRouter.Built from the 8 ImageRouter tools below, on the connection you add once.

What you can do with ImageRouter

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.

Image, 2 operations

edit_imageEdit imagePOSTGenerates images from ONE uploaded source image file (and an optional mask file) plus a prompt, with an image model that accepts image input. Billed to the account's credits. Returns hosted image URLs or base64, plus the cost.
generate_imageGenerate imagePOSTGenerates images with the chosen model from a text prompt, or from source images passed as URLs or data URIs. Billed to the account's credits. Returns hosted image URLs (kept 30 days) or base64, plus the cost.

Model, 2 operations

get_modelGet modelGETReturns one ImageRouter model by id: its modalities, price, supported parameters and allowed sizes and durations. Use it to check what a model accepts before generating. Public data, no credential needed.
list_modelsList modelsGETLists ImageRouter's models (image, video and text) with their modalities, prices, supported parameters and allowed sizes and durations. Filter by output_modalities, input_modalities, provider, free or name. Public data, no credential needed.

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTRuns an OpenAI-compatible chat completion with a text model (non-streaming) and returns the assistant message, token usage and the cost. Billed to the account's credits at the model's token price.

Credit, 1 operation

get_creditsGet creditsGETReturns the account's credit balance in USD: remaining credits, total usage and completed deposits; with by_api_key=true also the usage, spend limit and expiry of each API key.

Response, 1 operation

create_responseCreate responsePOSTRuns an OpenAI-compatible Responses call with a text model (non-streaming) and returns the output items, token usage and the cost. Billed to the account's credits at the model's token price.

Video, 1 operation

generate_videoGenerate videoPOSTGenerates a video with the chosen video model from a text prompt and/or one start image (URL or data URI). Billed to the account's credits. Waits for the result and returns the hosted video URL (kept 30 days) or base64, plus the cost.

Use ImageRouter from Claude Code, Cursor or Codex

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

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