Generate images and videos (GPT Image, Seedance, Kling, Wan, Qwen) with one API key.
Scored across 8 tools
Tools split cleanly into job lifecycle (submit/check/result/cancel), model discovery (search/schema/pricing), and execution (run_model). Minor overlap between check_job and get_job_result (both return status/wait) and between run_model and submit_job (sync vs queued), but descriptions clarify the boundaries.
All tools follow a consistent snake_case verb_noun pattern (submit_job, check_job, get_job_result, search_models, get_pricing). No mixed conventions or vague standalone verbs.
Eight tools is well-scoped for a model-execution/queue server, with each tool covering a distinct part of the workflow. No filler tools.
Job lifecycle is fully covered (submit, status, result, cancel) along with model discovery and execution. Minor gaps like a plain list_models (search_models likely substitutes) or account/usage tools are not blocking.
Cancel a request while it is still queued.
Inputs: model (required), request_id (required).
Status of a queued request (IN_QUEUE / IN_PROGRESS / COMPLETED / FAILED / CANCELLED) with position, logs and metrics.
Inputs: model (required), request_id (required), logs.
Result of a completed request; waits up to timeout seconds (max 60) when still running.
Inputs: model (required), request_id (required), timeout.
Input parameters (name, type, allowed values, defaults) and output shape for every task a model supports.
Inputs: model (required).
Live price per image, per second of video, or per video clip, depending on the model. Query one model or all models.
Inputs: model.
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.
Inputs: input (required), model (required), task.
Search the model catalog. Returns ids, modality, tasks, pricing and links. Use before calling run_model or submit_job to pick a model id.
Inputs: q, task, modality, available.
Queue a request and return its request_id immediately. Follow with check_job / get_job_result.
Inputs: input (required), model (required), task, webhook, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Generate images and videos with 200+ AI models (GPT-Image-2, Seedance, Veo, Kling) via one API.
Generate AI images and videos with Seedance, Kling, Veo, Sora, Nano Banana and more, one balance.
Best Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.
Generate images and videos with Seedream, GPT Image, Nano Banana, Kling and Seedance on one key.
Add one secure layer between your agents and this server.
