Free SiliconFlow API Key, Base URL & Rate Limits

API Provider

SiliconFlow is a Chinese AI inference platform offering generous free tiers for DeepSeek, Qwen, BGE, and other models popular in the Chinese LLM ecosystem.

OpenAI CompatibleFree Tier

Save API Key Test API Key Get API Key Docs

How to get a free SiliconFlow API key

1
Sign up at cloud.siliconflow.cn Phone verification. No credit card.
Get SiliconFlow API key →
2
Go to API Keys
3
Create an API key
4
Choose a model DeepSeek-V3, Qwen3, BGE available. 1,000 RPM free.
5
Configure OpenAI client Base URL: https://api.siliconflow.cn/v1

Provider Snapshot

P Provider Type API Provider

O OpenAI Compatible Yes

U Base URL https://api.siliconflow.cn/v1

F Free Tier 2 free models online

P Phone Required No

S Streaming Varies

T Function Calling Varies

V Vision Varies

L Last Updated 2026-06-14

Supported Models 3 models

View in directory →

Model ID	Developer	Context	Availability	Free Tier	Use cases
abbreviation Abbreviation	SiliconFlow	131K	Online	Yes	chat
deepseek-ai-deepseek-r1-distill-qwen-7b deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	SiliconFlow	131K	Online	Yes	chatreasoning
deepseek-ai-deepseek-ocr deepseek-ai/DeepSeek-OCR	SiliconFlow	131K	Check provider	Yes	chat

Developer Tools

K Save API Key Never lose your API keys — save keys from all providers in one place. T Test API Key Test your API key and check quota.

SiliconFlow FreeLLM Score free API access score

How we score →

42 /100

🔹 Niche Provider — Consider for easy signup

Generosity Free limits and access terms

Access Signup and key availability

Model Breadth Free model coverage

Reliability Status and stability signals

Compatibility SDK and endpoint support

Quality Model capability signals

What is SiliconFlow?

China-based free LLM API — DeepSeek, Qwen, BGE at 1,000 RPM.

SiliconFlow is a Chinese AI inference platform offering generous free tiers for DeepSeek, Qwen, BGE, and other models popular in the Chinese LLM ecosystem. The free tier supports up to 1,000 RPM and 50K TPM with no credit card required. Best latency for users in China and Asia-Pacific.

1,000 RPM, 50K TPM free tier
DeepSeek, Qwen, BGE models
Lowest latency for China-based users
OpenAI-compatible endpoint

API Compatibility: Live-tested OpenAI-compatible Chat Completions

SiliconFlow Free Tier Limits & Pricing

Credit Card Not required

Phone Verification Not required

Free Tier 2 free models online

Context Range 131K – 131K

Total Models 3 listed

Rate Limits 30 RPM, 60K TPM

API Compatibility Live-tested OpenAI-compatible Chat Completions

SiliconFlow API Setup Tutorials

Claude Code Environment variables and base URL setup Codex OpenAI-compatible config for local coding Gemini CLI Provider-specific API key routing notes

SiliconFlow is fully compatible with popular AI coding assistants like Cursor, Claude Code, and more. To see step-by-step API configuration instructions for your favorite tool, please visit our Global Configuration Guide →

SiliconFlow Model Use Cases

What SiliconFlow's free models are best for, based on aggregated model capabilities:

Chat 3 models Reasoning 1 model

SiliconFlow Limitations & Caveats

China-hosted — high latency outside Asia-Pacific
Chinese phone number required for registration
Model availability may change based on local regulations

SiliconFlow FAQ

Can overseas users register for SiliconFlow?

SiliconFlow currently requires a Chinese phone number for registration. International users may not be able to sign up without a Chinese number. Consider alternative providers like Groq or OpenRouter.

Is SiliconFlow faster than other providers for users in China?

Yes — SiliconFlow's servers are in mainland China, offering the lowest latency for Chinese users (typically under 100ms). This makes it ideal for China-based applications.

What models does SiliconFlow offer that others don't?

SiliconFlow specializes in Chinese ecosystem models: DeepSeek, Qwen, BGE embeddings, and Yi models. Some of these models are available elsewhere, but SiliconFlow often has the most up-to-date versions.