AI Agents
Use SeedRouter from AI Agents
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.
| Way | Best for | Setup |
|---|---|---|
| MCP server | Claude Code, Cursor, Codex, VS Code and other MCP clients | Add https://api.seedrouter.ai/v1/mcp with your API key as a Bearer header |
| Agent skill | Agents that load Agent Skills | The skill index is at /.well-known/agent-skills/index.json |
| HTTP API | Your own code, or an agent writing code for you | Quickstart |
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_KEYThe 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
- Find a model:
list_modelsover MCP, or the model list in/llms.txt. Each model with a landing page has a plain-text summary athttps://seedrouter.ai/models/<slug>/llms.txtwith its parameters, prices and examples. - Read its input schema:
get_model_schemaover MCP, or the model's documentation page. - 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. - Check the price:
get_pricingover MCP returns the model's current rates in USD before anything is submitted. - Submit and wait:
submit_task, thenget_taskwithwait_seconds: 50until the task finishes. Over HTTP, submit to the model's endpoint and pollGET /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
| Limit | Default | Response when exceeded |
|---|---|---|
| Image and video tasks in progress at once, per account | 50 | HTTP 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
| URL | What it is |
|---|---|
/llms.txt | Index of models, documentation and guides for language models |
/models/<slug>/llms.txt | One model's parameters, prices and examples |
/docs/<page>.md | Any documentation page as Markdown, for example /docs/api/overview.md |
/.well-known/agent-skills/index.json | Agent skill index |
/.well-known/api-catalog | API catalog (RFC 9727) |
https://api.seedrouter.ai/v1/mcp | MCP server |
