StepFun AI
stepfun-aiStepFun AI has one model in the ModelRunner catalog: GOT-OCR 2.0, an Image-to-Text endpoint, priced at $0.05 per response — extract text from documents, receipts, and scans (OCR).
1 public model — runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
StepFun AI models & pricing
What you can build with StepFun AI models
- Extract text from documents, receipts, and scans (OCR) GOT-OCR 2.0
- Read tables, formulas, and charts from images into text GOT-OCR 2.0
- Digitize printed or handwritten content GOT-OCR 2.0
Browse by capability
Use StepFun AI models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every StepFun AI model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What StepFun AI models can I run on ModelRunner?
The catalog has 1 public StepFun AI model: GOT-OCR 2.0. It covers image-to-text. It has its own page with a free playground, the full input schema, and copy-paste code.
How much do StepFun AI models cost?
Pay-per-use, with no subscription: the one StepFun AI model billed per response costs $0.05, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a StepFun AI model from the API?
POST to https://queue.modelrunner.run/stepfun-ai/got-ocr/v2 with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run StepFun AI model from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and StepFun AI's model becomes a tool your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.