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 1 API on the APIs.io network: Realtime API. Tagged areas include AI, Artificial Intelligence, LLM, Multimodal, and Chat Completion.

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
44.7/100 thin ▬ flat Agent 45/100 agent ready Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
12 APIs 1 MCP Servers
AIArtificial IntelligenceLLMMultimodalChat CompletionAudioSpeechText to SpeechSpeech RecognitionImagesRealtimeVector StoresChina

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 44.7/100 · thin
Contract Quality 7.0 / 25
Developer Ergonomics 13.0 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 5.8 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 45/100 · agent ready
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
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 4 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. 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. Want it done for you? Prioritized profiling — $2,500 →

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.yml

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
ErrorCatalog
 Conventions
Conventions
 Conformance
Conformance
 Lifecycle
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)

apis.yml Raw ↑ 
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
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- 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:
  - 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:
  - 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:
  - 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:
  - 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
  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
  - 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:
  - Images
  - Image Generation
  - Image Editing
  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:
  - 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:
  - 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