AIFreeForever AI Models API
Read-only access to the live AI model endpoints exposed by AIFreeForever. Send text, code, or a base64-encoded image/file to a selected currently available model and receive its generated answer; the model catalog is also exposed live.
Connect your agent
Connect through MCP so your agent can find this API, read its docs, and call its endpoints.
Add the server from your terminal.
claude mcp add --transport http agent-data https://agent-data.motie.dev/mcpIn Claude Code, run /mcp, select agent-data, then Authenticate. Sign in to your agent-data account in the browser.
Then ask your agent to use the AIFreeForever AI Models API for your task.
Call it over HTTP
Get an API keySign up free, generate an API key, and set it as AGENT_DATA_API_KEY in your environment. Your first 100 calls each month are free.
curl --request GET --get 'https://3kpkg0jfvk.execute-api.us-east-2.amazonaws.com/prod/b46a92eb-c751-408d-80ab-1330f74487ef/v1/chat' \
--header "Authorization: Bearer $AGENT_DATA_API_KEY" \
--data-urlencode 'question=Explain this Python function and suggest a safer implementation.'Endpoints
Inputs and response fields for every endpoint in this API.
GETChat/v1/chat
Send a text question, including code, to a currently available model. If the requested source provider returns a retryable provider failure, the service may use another currently available source model; requested_model and fallback_used make that adaptation explicit. For photos or other files, provide strict base64 data plus its MIME type and filename; the API forwards the source-observed file object to the model.
Input
questionRequiredQuery · stringText prompt or source code to send to the selected AI model.
Example: Explain this Python function and suggest a safer implementation.
modelOptionalQuery · string, default: gpt-5Current AIFreeForever model ID; obtain fresh IDs from GET /v1/models.
Example: gpt-5
file_base64OptionalQuery · string | nullOptional strict base64 bytes for an image, code file, or document.
Example: iVBORw0KGgo=
file_mime_typeOptionalQuery · string | nullMIME type for file_base64, such as image/png or text/plain.
Example: image/png
file_nameOptionalQuery · string | nullFilename for file_base64, such as photo.png or main.py.
Example: photo.png
Response
modelstringanswerstringeventsobject[]attemptsobject[]attempts[].model?string | nullattempts[].stagestringattempts[].status?integer | nullattempts[].response?string | nullquestionstringstreamedbooleanfile_name?string | nulltransportstringmodel_namestringraw_responsestringfallback_usedbooleanfile_attachedbooleanrequested_modelstringsource_endpointstringFields marked ? are optional.
GETModels/v1/models
Fetch the live model catalog. Use an available model ID from this response with GET /v1/chat.
Input
No input parameters.
Response
modelsobject[]models[].idstringmodels[].why?string | nullmodels[].hrefstringmodels[].namestringmodels[].pagestringmodels[].endpoint?string | nullmodels[].availablebooleanmodels[].configured?boolean | nullattemptsobject[]attempts[].model?string | nullattempts[].stagestringattempts[].status?integer | nullattempts[].response?string | nulltransportstringsource_endpointstringupstream_catalogobjectFields marked ? are optional.
Don’t see the endpoint you need?
Ask agent-data to add an endpoint or return more fields. Extensions are free and keep existing endpoints working.
An account is required to submit an extension. Prepare your request, then sign in to build.