Generate images and videos (GPT Image, Seedance, Kling, Wan, Qwen) with one API key.
Score is being calculated.
Cancel a request while it is still queued.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model id | |
| request_id | Yes | req_… id |
Status of a queued request (IN_QUEUE / IN_PROGRESS / COMPLETED / FAILED / CANCELLED) with position, logs and metrics.
| Name | Required | Description | Default |
|---|---|---|---|
| logs | No | ||
| model | Yes | Model id | |
| request_id | Yes | req_… id |
Result of a completed request; waits up to timeout seconds (max 60) when still running.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model id | |
| timeout | No | ||
| request_id | Yes | req_… id |
Input parameters (name, type, allowed values, defaults) and output shape for every task a model supports.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model id, e.g. gpt-image-2 |
Live price per image or per video clip for one model or all models.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model id; omit for all models |
Run a model synchronously with the caller's API key. Images return URLs; videos are queued and this waits up to 60 s before returning the queue status instead.
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | Force the task kind (inferred otherwise) | |
| input | Yes | Model input: prompt, size, n, image, seconds … | |
| model | Yes | Model id |
Search the model catalog. Returns ids, modality, tasks, pricing and links. Use before calling run_model or submit_job to pick a model id.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free-text query over id, name, vendor and tags | |
| task | No | text-to-image | image-to-image | text-to-video | image-to-video | |
| modality | No | image or video | |
| available | No | Only models live on the gateway |
Queue a request and return its request_id immediately. Follow with check_job / get_job_result.
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | Force the task kind (inferred otherwise) | |
| input | Yes | ||
| model | Yes | Model id | |
| webhook | No | Public http(s) URL to POST the result to | |
| priority | No | normal or low |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
cancel_jobcheck_jobget_job_resultget_model_schemaget_pricingrun_modelsearch_modelssubmit_jobBest Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.
Make AI video, images and voice with Seedance, Kling, Veo, Nano Banana, GPT Image and more.
Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.
One API for 100+ AI video, image, music and speech models.
Add one secure layer between your agents and this server.
