API & MCP

Programmatic access to the directory — built for on-demand lookups by humans, scripts, and agents. No API key needed yet; fair-use rate limits apply. There is deliberately no bulk export.

01REST API

Endpoint	Returns
GET /api/v1/models	thin list — ids, names, creators
GET /api/v1/models/{id}	full entry: attributes, offerings with provider IDs + pricing, benchmarks
GET /api/v1/agents · /agents/{id}	same for agents: interfaces, install, invoke methods
GET /api/v1/providers · /providers/{id}	auth model, base URL, docs links
GET /api/v1/search?q=&type=	token search across names, ids, creators, provider model IDs
GET /api/v1/snippet?model=&provider=&language=	working invocation code, provider ID substituted

shell

curl https://invokeable.ai/api/v1/models/claude-sonnet-4-5
curl "https://invokeable.ai/api/v1/search?q=cheap+vision+1m+context"
curl "https://invokeable.ai/api/v1/snippet?model=claude-sonnet-4-5&provider=aws-bedrock&language=python"

02MCP endpoint

Give your agent the directory as tools — it stops hallucinating model IDs and prices. Streamable HTTP, stateless, no auth: add https://invokeable.ai/mcp as a custom connector in Claude, or wire it into any MCP client.

find models/agents/providers by any identifier

get_model

full model entry incl. every provider's exact ID

get_agent

full agent entry incl. install + invoke code

get_snippet

invocation code for model × provider × language

whats_available

thin index of everything in the directory

shell · tools/list

curl -X POST https://invokeable.ai/mcp \
  -H "content-type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

03Access policy

Everything here is free for on-demand use: look up a model, wire the API into your app, let your agent query it on every run. What we don't offer is a bulk dump — aggregating and keeping this fresh is the work, so wholesale copies aren't a download away. If you need broader access, talk to us.