API operations
One API key for multiple model types
Use the ModelPort API to check availability, request quotes, submit jobs, and retrieve results and charges.
Choose an endpoint
Submit image, video, and audio jobs with POST /v1/jobs. OpenAI-compatible image clients can use /v1/images/generations or /v1/images/edits. Text clients can use /v1/chat/completions or /v1/messages when the chosen model is available.
Check availability first
Use GET /v1/models to read model IDs, allowed parameters, and the available flag. Configure OpenAI SDK clients with a base URL ending in /v1. For the Anthropic SDK, use the domain without the /v1 suffix.
Quote, submit, and check the charge
Request a quote before submitting. Keep the same Idempotency-Key when retrying the same job after a timeout. Read the result at GET /v1/jobs/{id} and the charge at GET /v1/records/{id}.
Connect a client
Use list_models to verify the MCP connection in a supported client. If you use webhooks, verify the ModelPort signature before processing a delivery.
Example request
curl "https://api.apimodel.store/v1/models" \ -H "Authorization: Bearer $MODELPORT_API_KEY"