Claude Opus 5.5 is live on SeedRouter

AI Agents

Use SeedRouter from AI Agents

View Markdown

Connect coding agents and AI assistants to SeedRouter with the MCP server, the agent skill or the HTTP API, and the limits an agent should plan around.

An agent can use SeedRouter in three ways. They share the same API key, balance, models and limits, and they are billed the same.

WayBest forSetup
MCP serverClaude Code, Cursor, Codex, VS Code and other MCP clientsAdd https://api.seedrouter.ai/v1/mcp with your API key as a Bearer header
Agent skillAgents that load Agent SkillsThe skill index is at /.well-known/agent-skills/index.json
HTTP APIYour own code, or an agent writing code for youQuickstart

To run the agent itself on SeedRouter's text models instead, see Coding agents on SeedRouter.

Set your key once

Create a key on the API keys page and export it, so the agent can read it without the key landing in your project files:

export SEEDROUTER_API_KEY=YOUR_API_KEY

The API keys page also has a Connect via MCP button that prints a ready setup for each MCP client.

What an agent does on SeedRouter

  1. Find a model: list_models over MCP, or the model list in /llms.txt. Each model with a landing page has a plain-text summary at https://seedrouter.ai/models/<slug>/llms.txt with its parameters, prices and examples.
  2. Read its input schema: get_model_schema over MCP, or the model's documentation page.
  3. Use public media URLs: generation endpoints accept reference images, videos and audio only as public http(s) URLs. Base64 input is rejected, so host local files somewhere reachable first.
  4. Check the price: get_pricing over MCP returns the model's current rates in USD before anything is submitted.
  5. Submit and wait: submit_task, then get_task with wait_seconds: 50 until the task finishes. Over HTTP, submit to the model's endpoint and poll GET /v1/tasks/{id} about every three seconds.

Failed tasks are not charged. A submission is not idempotent: retrying a request whose response you did not receive creates and charges a second task, so check your task history or balance first.

Limits to plan around

LimitDefaultResponse when exceeded
Image and video tasks in progress at once, per account50HTTP 429, code 30002

Requests can also be rate limited, which returns HTTP 429 as well. On HTTP 429, wait for Retry-After when it is present; otherwise back off exponentially with jitter and a cap. Base the decision on the status code rather than parsing error bodies, because the text endpoints answer in the error format of their protocol. A batch job should keep a queue and submit new tasks as running ones finish, rather than sending everything at once. Contact [email protected] if you need a higher limit.

Machine-readable entry points

URLWhat it is
/llms.txtIndex of models, documentation and guides for language models
/models/<slug>/llms.txtOne model's parameters, prices and examples
/docs/<page>.mdAny documentation page as Markdown, for example /docs/api/overview.md
/.well-known/agent-skills/index.jsonAgent skill index
/.well-known/api-catalogAPI catalog (RFC 9727)
https://api.seedrouter.ai/v1/mcpMCP server