Featured models
Model IDs you can call through FishToken, grouped by what they produce. Use the ID exactly as shown in the model field of your request.
Video
Endpoint: POST https://fishtoken.ai/v1/video/generations. Video generation runs as a task: you submit a request, then check the task until the video is ready. Not sure which family to start with? Compare the four video APIs.
Seedance 2.0 Fast
doubao-seedance-2-0-fast-260128doubao-seedance-2-0-260128doubao-seedance-2-5-260628
Video generation. The Fast variant plus the standard Seedance 2.0 and Seedance 2.5 IDs.
Wan 2.7 (video)
wan2.7-t2vwan2.7-i2vwan2.7-r2vwan2.7-videoedit
Text-to-video, image-to-video, reference-to-video and video editing.
Text
Endpoint: POST https://fishtoken.ai/v1/chat/completions, compatible with the OpenAI SDK.
DeepSeek V4 Flash
deepseek-v4-flash
Text and code: captions, product copy, support replies, code help.
Image
Endpoints: POST https://fishtoken.ai/v1/images/generations and /v1/images/edits.
Availability and prices can change. The live model list and current prices are on fishtoken.ai/pricing; request formats are in the FishToken docs.
Guides
Longer walkthroughs with runnable code.
Chinese AI video APIs compared
Seedance, Kling, Wan and Vidu side by side: model IDs, modes, endpoint, and one example that switches models by changing one field.
Switch an OpenAI SDK project in two lines
Point an existing Python or Node.js project at FishToken with base_url and api_key, or with two environment variables.
Seedance 2.0 Fast in Python
A complete script: submit a generation, poll the task, save the result URL. With prompt tips.
Get your API key
Create an account, add balance, and make your first call from the quickstart.