StepFun
StepFun (阶跃星辰) is a Shanghai-based AI foundation-model company whose open platform serves the Step model family — multimodal reasoning (step-3.7-flash), fast language reasoning (step-3.5-flash), vision, image generation and editing (step-2x-large, step-image-edit-2), and a deep audio stack spanning TTS, voice cloning, ASR, and end-to-end realtime voice (StepAudio 2.5) — via an OpenAI-compatible REST API at api.stepfun.com, an Anthropic-compatible Messages API, WebSocket realtime channels, and a hosted StepSearch MCP server for agent clients.
Limited machine-readable signal and partial portal coverage — documentation a human can read, but little a machine or agent can consume without scraping.
API Evangelist profiles StepFun the way a machine reads it — 17 machine-readable artifacts across 12 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — StepFun scores 44.7/100 (thin), with a separate agent-readiness read of 45/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile StepFun
Each block below is one kind of artifact we hold for StepFun. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 12
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
StepFun Chat Completions API
OpenAI-compatible chat completions for the Step model family (e.g. step-3.7-flash, step-3.5-flash, stepaudio-2.5-chat), with multimodal image/video/audio message parts, tool cal...
StepFun Messages API
Anthropic Messages API-compatible endpoint (POST /v1/messages) that lets the Anthropic SDK and Claude-style JSON structures run against Step models by pointing base_url at https...
StepFun Responses API
OpenAI Responses API-style endpoint for generating model responses on the StepFun open platform.
StepFun Models API
List available Step models, retrieve a single model, and inspect the model object.
StepFun Audio API
Speech synthesis (TTS), voice cloning with preview, official voice catalog, audio transcription, and file-based / streaming speech recognition (ASR) across the StepAudio 2.5 and...
StepFun Realtime API
Bidirectional realtime voice over WebSocket (wss://api.stepfun.com/v1/realtime) with OpenAI Realtime-style session, conversation, and response events, plus a streaming TTS chann...
StepFun Images API
Image generation, image editing, and image-to-image endpoints for the step-2x-large and step-image-edit-2 models.
StepFun Files API
Upload, list, retrieve, delete files and fetch file content for use with Step models and knowledge bases.
StepFun Vector Stores API
Knowledge-base (vector store) management — create/list/retrieve/delete stores and attach or remove files for retrieval-augmented generation.
StepFun Web Search API
Web search and text-to-image search endpoints (POST /v1/search) billed per call as value-added capabilities.
StepFun Token Count API
Pre-count prompt tokens for a model request (POST /v1/token/count) to estimate usage and cost.
StepFun Accounts API
Retrieve account information including balances (GET /v1/accounts).
Scroll within the panel for all 12 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
stepfun-mcp.yml
MCP SERVERRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Stepfun Rate Limits
RATE LIMITSEvent Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
StepFun Realtime Voice & Streaming TTS WebSocket API
StepFun's realtime event surface: a bidirectional realtime voice channel at wss://api.stepfun.com/v1/realtime (OpenAI Realtime-style session / conversation / response events, mo...
ASYNCAPISecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Resources
Every other property we hold for StepFun — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 3
Portal, sign-up, and the first successful call
Documentation 3
Reference material describing how the API behaves
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 4
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 3
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 1
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/stepfun · machine-readable index on apis.io