SiliconFlow — Free LLM API

8 free models available — credit card may be required. Get API key →

All Free SiliconFlow Models — Context Windows & Rate Limits

Model Context Max Output Modality Rate Limit Status
Qwen/Qwen3-8B 131K 131K text 1,000 RPM, 50K TPM Details
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 33K 16K text 1,000 RPM, 50K TPM Details
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 131K 131K text 1,000 RPM, 50K TPM Details
THUDM/glm-4-9b-chat 32K 32K text 1,000 RPM, 50K TPM Details
THUDM/GLM-4.1V-9B-Thinking 66K 66K text 1,000 RPM, 50K TPM Details
deepseek-ai/DeepSeek-OCR 131K 8K text 1,000 RPM, 50K TPM Details
+ embedding/speech models 131K 131K textaudio 1,000 RPM, 50K TPM Details
Abbreviation 131K 8K text See provider page Details

Frequently Asked Questions about SiliconFlow Free API

Is SiliconFlow free to use?

SiliconFlow offers a permanently free tier with 8 available models. Account creation is required, and a credit card may be needed to activate the free tier.

What models does SiliconFlow offer for free?

SiliconFlow provides 8 free models covering chat, reasoning, audio, embedding use cases. Supported modalities include text, audio. Browse the full list above with context windows and rate limits.

How do I use SiliconFlow with Claude Code or Cursor?

Click "Details" on any model above to get one-click configuration snippets for Claude Code (cc), Cursor, Codex, and more. All SiliconFlow models listed here use an OpenAI-compatible endpoint, so any tool that accepts a custom baseURL will work.