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.

StepFun publishes 12 APIs on the APIs.io network, including Realtime API, and 11 more. Tagged areas include Artificial Intelligence, LLM, Multi-Modal, Chat Completions, and Audio.

The StepFun catalog on APIs.io includes 1 event-driven AsyncAPI specification.

StepFun’s developer surface includes documentation, API reference, getting-started guide, support, pricing, signup flow, authentication, and 18 more developer resources.

🌐 Visit website 📡 Source on GitHub

47.9/100 developing ▬ flat Agent 31/100 agent ready saas Full breakdown ↓
scored 2026-09-25 · rubric v0.23.0

12 APIs 1 MCP Servers

Artificial Intelligence LLM Multi-Modal Chat Completions Audio Speech Text-to-Speech Speech Recognition Image Real-Time Vector Stores China

Kin Score

Kin Score How this is scored →
scored 2026-09-25 · rubric v0.23.0

Composite quality — 47.9/100 · developing

Contract Quality 8.4 / 21

Developer Ergonomics 10.5 / 17

Access Clarity 7.6 / 17

Operational Transparency 4.7 / 11

Contract Governance 1.9 / 10

Discoverability 6.8 / 9

Regulatory Posture 3.4 / 15

Agent readiness — 31/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/stepfun: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 1

Interfaces this provider implements that became standards by being copied rather than ratified. Each is profiled by the API Commons, and the evidence column says how the claim was established — not that it was made.

The OpenAI Interface

prose — states compatibility; nothing published to check it against

2 core of 338 operations graded · api-commons/models

APIs 12

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 for all 12

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

StepFun MCP Server

StepFun operates an official hosted remote MCP server, StepSearch — a search service built on the Model Context Protocol that gives Claude Code, Cline, OpenCode, Goose, and othe...

MCP SERVER

Rate Limits 1

Documented rate limits and quota policies.

Stepfun Rate Limits

18 limits

RATE LIMITS

Event Specifications 1

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...

ASYNCAPI

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Stepfun Authentication

http-bearer-api-key · 1 scheme

SECURITY

Stepfun Domain Security

TLSv1.3 · DNSSEC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 3

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

AsyncAPI

AsyncAPI

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

WellKnown

WellKnown

MCPServer

MCPServer

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

ErrorCatalog

Conventions

Conformance

Lifecycle

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

SDKs

SDKs

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 3

Status, limits, changes, and where to get help

Support

Support

RateLimits

RateLimits

Deprecation

Deprecation

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 1

The organization behind the API

Website

Website

Source (apis.yml)

aid: stepfun
name: StepFun
description: 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.
url: https://raw.githubusercontent.com/api-evangelist/stepfun/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- qiming
x-tier: enriched
x-tier-reason: live-api-provider
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - rate-limits
  - security
  generated: '2026-09-03'
  method: derived
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Artificial Intelligence
- LLM
- Multi-Modal
- Chat Completions
- Audio
- Speech
- Text-to-Speech
- Speech Recognition
- Image
- Real-Time
- Vector Stores
- China
tags_raw:
- AI
- Artificial Intelligence
- LLM
- Multimodal
- Chat Completion
- Audio
- Speech
- Text to Speech
- Speech Recognition
- Images
- Realtime
- Vector Stores
- China
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/stepfun.png
apis:
- aid: stepfun:chat-completions-api
  name: StepFun Chat Completions API
  description: 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 calling, JSON mode, streaming via SSE, reasoning output, and prompt
    caching with discounted cache-hit pricing.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/chat/chat-completion-create
  baseURL: https://api.stepfun.com
  tags:
  - Artificial Intelligence
  - LLM
  - Chat Completions
  - Multi-Modal
  - Tool Calling
  tags_raw:
  - AI
  - LLM
  - Chat Completion
  - Multimodal
  - Tool Calling
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/chat/chat-completion-create
- aid: stepfun:messages-api
  name: StepFun Messages API
  description: 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://api.stepfun.com.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/chat/messages-create
  baseURL: https://api.stepfun.com
  tags:
  - Artificial Intelligence
  - LLM
  - Message
  - Anthropic Compatible
  tags_raw:
  - AI
  - LLM
  - Messages
  - Anthropic Compatible
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/chat/messages-create
- aid: stepfun:responses-api
  name: StepFun Responses API
  description: OpenAI Responses API-style endpoint for generating model responses on the StepFun open platform.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/responses/responses-create
  baseURL: https://api.stepfun.com
  tags:
  - Artificial Intelligence
  - LLM
  - Responses
  tags_raw:
  - AI
  - LLM
  - Responses
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/responses/responses-create
- aid: stepfun:models-api
  name: StepFun Models API
  description: List available Step models, retrieve a single model, and inspect the model object.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/models/list
  baseURL: https://api.stepfun.com
  tags:
  - Artificial Intelligence
  - Models
  - Catalog
  tags_raw:
  - AI
  - Models
  - Catalog
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/models/list
- aid: stepfun:audio-api
  name: StepFun Audio API
  description: 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 step-tts model families.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/audio/create-audio
  baseURL: https://api.stepfun.com
  tags:
  - Audio
  - Text-to-Speech
  - Speech Recognition
  - Voice Cloning
  tags_raw:
  - Audio
  - Text to Speech
  - Speech Recognition
  - Voice Cloning
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/audio/create-audio
- aid: stepfun:realtime-api
  name: StepFun Realtime API
  description: Bidirectional realtime voice over WebSocket (wss://api.stepfun.com/v1/realtime) with OpenAI Realtime-style
    session, conversation, and response events, plus a streaming TTS channel at /v1/realtime/audio.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/realtime/chat
  baseURL: https://api.stepfun.com
  tags:
  - Audio
  - Real-Time
  - WebSocket
  - Voice
  tags_raw:
  - Audio
  - Realtime
  - WebSocket
  - Voice
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/realtime/chat
  - type: AsyncAPI
    url: asyncapi/stepfun-realtime-asyncapi.yml
- aid: stepfun:images-api
  name: StepFun Images API
  description: Image generation, image editing, and image-to-image endpoints for the step-2x-large and step-image-edit-2 models.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/images/image
  baseURL: https://api.stepfun.com
  tags:
  - Image
  - Image Generation
  - Image Editing
  tags_raw:
  - Images
  - Image Generation
  - Image Editing
  - Image-Generation
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/images/image
- aid: stepfun:files-api
  name: StepFun Files API
  description: Upload, list, retrieve, delete files and fetch file content for use with Step models and knowledge bases.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/files/create
  baseURL: https://api.stepfun.com
  tags:
  - File
  - Storage
  tags_raw:
  - Files
  - Storage
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/files/create
- aid: stepfun:vector-stores-api
  name: StepFun Vector Stores API
  description: Knowledge-base (vector store) management — create/list/retrieve/delete stores and attach or remove files for
    retrieval-augmented generation.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/vector-stores/create
  baseURL: https://api.stepfun.com
  tags:
  - Vector Stores
  - RAG
  - Knowledge Base
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/vector-stores/create
- aid: stepfun:web-search-api
  name: StepFun Web Search API
  description: Web search and text-to-image search endpoints (POST /v1/search) billed per call as value-added capabilities.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/search/search
  baseURL: https://api.stepfun.com
  tags:
  - Search
  - Web Search
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/search/search
- aid: stepfun:token-count-api
  name: StepFun Token Count API
  description: Pre-count prompt tokens for a model request (POST /v1/token/count) to estimate usage and cost.
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/token-count
  baseURL: https://api.stepfun.com
  tags:
  - Tokens
  - Utility
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/token-count
- aid: stepfun:accounts-api
  name: StepFun Accounts API
  description: Retrieve account information including balances (GET /v1/accounts).
  humanURL: https://platform.stepfun.com/docs/zh/api-reference/accounts/get
  baseURL: https://api.stepfun.com
  tags:
  - Account
  - Billing
  tags_raw:
  - Accounts
  - Billing
  properties:
  - type: Documentation
    url: https://platform.stepfun.com/docs/zh/api-reference/accounts/get
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/stepfun-domain-security.yml
- type: Website
  url: https://www.stepfun.com
- type: DeveloperPortal
  url: https://platform.stepfun.com
- type: Documentation
  url: https://platform.stepfun.com/docs
- type: APIReference
  url: https://platform.stepfun.com/docs/zh/api-reference/chat/chat-completion-create
- type: GettingStarted
  url: https://platform.stepfun.com/docs/zh/quickstart/overview
- type: Support
  url: https://platform.stepfun.com/docs/zh/guides/contact-us
- type: GitHubOrganization
  url: https://github.com/stepfun-ai
- type: Pricing
  url: https://platform.stepfun.com/docs/zh/guides/pricing/details
- type: SignUp
  url: https://platform.stepfun.com
- type: TermsOfService
  url: https://platform.stepfun.com/docs/zh/agreement/userservice
- type: PrivacyPolicy
  url: https://platform.stepfun.com/docs/zh/agreement/userprivacy
- type: LLMsTxt
  url: llms/stepfun-llms.txt
- type: WellKnown
  url: well-known/stepfun-well-known.yml
- type: MCPServer
  url: mcp/stepfun-mcp.yml
- type: ErrorCatalog
  url: errors/stepfun-error-codes.yml
- type: RateLimits
  url: rate-limits/stepfun-rate-limits.yml
- type: Conventions
  url: conventions/stepfun-conventions.yml
- type: Authentication
  url: authentication/stepfun-authentication.yml
- type: Conformance
  url: conformance/stepfun-conformance.yml
- type: Lifecycle
  url: lifecycle/stepfun-lifecycle.yml
- type: Deprecation
  url: https://platform.stepfun.com/docs/zh/guides/model-migration
- type: Packages
  url: packages/stepfun-packages.yml
- type: SDKs
  url: packages/stepfun-packages.yml
- type: AsyncAPI
  url: asyncapi/stepfun-realtime-asyncapi.yml
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 12
  pass: local-v1

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/stepfun"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/stepfun/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/stepfun/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.