deepseek-ai/DeepSeek-R1-Distill-Qwen-7B — Free AI Model & API

siliconflow/deepseek-ai-deepseek-r1-distill-qwen-7b

chat reasoning

Get API key →

Context Window 131K

Max Output 131K

Rate Limit 1,000 RPM, 50K TPM

Cost $0.00 FREE

Free Period Since May 10, 2026

Credit Card Not required

Status Online

Overview

DeepSeek R1 distilled to Qwen 7B, available free on SiliconFlow's API. A compact reasoning model combining chain-of-thought deliberation with an efficient 7B footprint — suitable for lightweight math, logic, and coding tasks. SiliconFlow provides an OpenAI-compatible endpoint with low latency in China. Free tier requires registration.

Model ID

deepseek-ai-deepseek-r1-distill-qwen-7b

Base URL

https://api.siliconflow.cn/v1

Specifications

Context: 131K · Output: 131K · Modality: text · OpenAI Compat: Yes

Quick Start

Integrate deepseek-ai/DeepSeek-R1-Distill-Qwen-7B with 3 lines of code. See the config generator for Claude Code, Cursor, and more.

from openai import OpenAI

client = OpenAI(
 base_url="https://api.siliconflow.cn/v1",
 api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
 model="deepseek-ai-deepseek-r1-distill-qwen-7b",
 messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: "https://api.siliconflow.cn/v1",
 apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
 model: "deepseek-ai-deepseek-r1-distill-qwen-7b",
 messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://api.siliconflow.cn/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer YOUR_API_KEY" \
 -d '{
 "model": "deepseek-ai-deepseek-r1-distill-qwen-7b",
 "messages": [{"role": "user", "content": "Hello!"}]
 }'

Other Free Models from SiliconFlow

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

33K context · No card

THUDM/glm-4-9b-chat

32K context · No card

THUDM/GLM-4.1V-9B-Thinking

66K context · No card

deepseek-ai/DeepSeek-OCR

131K context · No card

Abbreviation

131K context · No card

Rate Limits & Constraints

Rate Limit 1,000 RPM, 50K TPM

Context Window 131K

Max Output Tokens 131K

Cost Free — since May 10, 2026

Credit Card Not required

OpenAI Compatible Yes — drop-in replacement

SiliconFlow Platform Limitations

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

Features & Use Cases

Best For

ChatReasoning

Modality Support

text

SiliconFlow Highlights

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

Playground — Test deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Test deepseek-ai/DeepSeek-R1-Distill-Qwen-7B directly in your browser. Your API key is sent directly to SiliconFlow — never stored.

Model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B Get Key

🔒 Your key is never stored — sent directly to the model provider via our server proxy.

Ready to chat with deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.

Frequently Asked Questions

How do I get an API key for deepseek-ai/DeepSeek-R1-Distill-Qwen-7B?

Sign up at SiliconFlow to get your API key. No credit card is required — just an email sign-up. Once you have the key, use the code snippets in the Quick Start section above.

Is deepseek-ai/DeepSeek-R1-Distill-Qwen-7B really free?

Yes. deepseek-ai/DeepSeek-R1-Distill-Qwen-7B is available on SiliconFlow's free tier and has been free since May 10, 2026. Rate limits apply: 1,000 RPM, 50K TPM. Always check the provider's terms for any changes to the free tier.

What are deepseek-ai/DeepSeek-R1-Distill-Qwen-7B's rate limits?

1,000 RPM, 50K TPM Context window: 131K. Max output: 131K. No credit card required.

What are the best free alternatives to deepseek-ai/DeepSeek-R1-Distill-Qwen-7B?

Popular free alternatives include inclusionAI: Ring-2.6-1T, Baidu Qianfan: CoBuddy (free), Owl Alpha. You can also browse all 147+ free models on our site.