SiliconFlow

SiliconFlow is an AI inference cloud serving a broad catalog of open-source models with OpenAI- and Anthropic-compatible APIs. Hosts DeepSeek-R1/V3, Qwen3-Coder, GLM-4.6V, Kimi-K2, MiniMax-M1-80k, gpt-oss-120b, Llama 3.3 70B, FLUX 1.1 Pro, Wan2.2 (video), CosyVoice2 and Fish-Speech (audio). Surfaces include chat, completions, embeddings, reranking, image, video, audio (speech + transcription + voice cloning), files, fine-tuning, and batch.

SiliconFlow publishes 1 API on the APIs.io network: Cloud Platform API. Tagged areas include AI, LLM, Inference, Open Source, and OpenAI Compatible.

SiliconFlow’s developer surface includes documentation, engineering blog, and 8 more developer resources.

🌐 Visit website 📡 Source on GitHub

33.7/100 thin ▬ flat Agent 19/100 agent aware Full breakdown ↓
scored 2026-08-05 · rubric v0.9.1

1 APIs

AILLMInferenceOpen SourceOpenAI CompatibleAnthropic CompatibleImage GenerationAudioVideo

Kin Score

Kin Score How this is scored →
scored 2026-08-05 · rubric v0.9.1

Composite quality — 33.7/100 · thin

Contract Quality 15.5 / 25

Developer Ergonomics 2.2 / 20

Commercial Clarity 5.8 / 20

Operational Transparency 3.4 / 13

Governance 0.0 / 12

Discoverability 6.9 / 10

Agent readiness — 19/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 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

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/siliconflow: 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 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Rate Limits 1

Documented rate limits and quota policies.

Siliconflow Rate Limits

1 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LlmsText

LlmsText

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

RateLimits

RateLimits

Commercial 2

Pricing, plans, and the legal terms of use

Plans

Plans

FinOps

FinOps

Company 3

The organization behind the API

LinkedIn

Website

Website

Blog

Blog

Source (apis.yml)

aid: siliconflow
url: https://raw.githubusercontent.com/api-evangelist/siliconflow/refs/heads/main/apis.yml
name: SiliconFlow
kind: company
description: SiliconFlow is an AI inference cloud serving a broad catalog of open-source models with OpenAI- and Anthropic-compatible
  APIs. Hosts DeepSeek-R1/V3, Qwen3-Coder, GLM-4.6V, Kimi-K2, MiniMax-M1-80k, gpt-oss-120b, Llama 3.3 70B, FLUX 1.1 Pro, Wan2.2
  (video), CosyVoice2 and Fish-Speech (audio). Surfaces include chat, completions, embeddings, reranking, image, video, audio
  (speech + transcription + voice cloning), files, fine-tuning, and batch.
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - plans
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/siliconflow.png
tags:
- AI
- LLM
- Inference
- Open Source
- OpenAI Compatible
- Anthropic Compatible
- Image Generation
- Audio
- Video
created: '2026-05-08'
modified: '2026-05-08'
specificationVersion: '0.19'
apis:
- aid: siliconflow:platform
  name: SiliconFlow Cloud Platform API
  description: OpenAI- and Anthropic-compatible inference covering chat completions, messages, embeddings, reranking, image
    generation, video (Wan2.2), audio (speech, transcription, voice cloning, voice list), files, fine-tuning, and batch. Pay-as-you-go
    with prepaid balance.
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.siliconflow.com/
  baseURL: https://api.siliconflow.com/v1
  tags:
  - AI
  - LLM
  - Chat Completions
  - Messages
  - Embeddings
  - Reranking
  - Image Generation
  - Video Generation
  - Audio
  - Files
  - Fine Tuning
  - Batch
  properties:
  - type: Documentation
    url: https://docs.siliconflow.com/
  - type: Signup
    url: https://siliconflow.com/
  - type: Pricing
    url: https://siliconflow.com/
  - type: APIReference
    url: https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions
common:
- type: DomainSecurity
  url: security/siliconflow-domain-security.yml
- type: GitHubOrganization
  url: https://github.com/siliconflow
- type: LinkedIn
  url: https://www.linkedin.com/company/siliconflow
- type: Website
  url: https://siliconflow.com/
- type: Documentation
  url: https://docs.siliconflow.com/
- type: Plans
  url: plans/siliconflow-plans-pricing.yml
- type: RateLimits
  url: rate-limits/siliconflow-rate-limits.yml
- type: FinOps
  url: finops/siliconflow-finops.yml
- type: LlmsText
  url: https://docs.siliconflow.com/llms.txt
- url: https://siliconflow.com/blog
  type: Blog
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

SiliconFlow

Kin Score

APIs 1

SiliconFlow Cloud Platform API

Pricing Plans 1

Siliconflow Plans Pricing