ModelScope
Alibaba’s hub: 50 free models over API, many of them frontier Chinese ones.
ModelScope is Alibaba’s public model hub. The inference API puts a large free catalogue in front of you — 50 models on the live list, MiniMax M3, Qwen 3.8, DeepSeek V4 and GLM among them — at 2,000 requests a day, OpenAI-compatible.
Sign-up wants a phone number — often a Chinese one — before the inference key works. 1M context on the long models. If you specifically want Qwen from the source, Alibaba Model Studio is the other door; ModelScope is the wider zoo.
- Free models
- 50
- Max context
- 1M
- Free tier
- 2,000 requests per day
- Requirement
- Phone verification, no card
Endpoint
Base URL
https://api-inference.modelscope.cn/v1Env var
MODELSCOPE_API_KEYRate limit
2,000 requests/day across all models- OpenAI-compatible
- text
- image
- audio
- video
- vision
- reasoning
Code examples
npm install openaiimport OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://api-inference.modelscope.cn/v1',
apiKey: process.env.MODELSCOPE_API_KEY
})
const response = await client.chat.completions.create({
model: 'MiniMax/MiniMax-M3',
messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})
console.log(response.choices[0].message.content)pip install openaiimport os
from openai import OpenAI
client = OpenAI(
base_url="https://api-inference.modelscope.cn/v1",
api_key=os.environ["MODELSCOPE_API_KEY"],
)
response = client.chat.completions.create(
model="MiniMax/MiniMax-M3",
messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)
print(response.choices[0].message.content)curl https://api-inference.modelscope.cn/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MODELSCOPE_API_KEY" \
-d '{
"model": "MiniMax/MiniMax-M3",
"messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
}'Worth knowing
- Registration needs a Chinese phone number for some account types.
Models you get for free50
- DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-Flash-0731 - DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro - DeepSeek V4 Pro 0813
deepseek-ai/DeepSeek-V4-Pro-0813 - EA 29B A4B
early-access/EA-29B-A4B - AntAngelMed
MedAIBase/AntAngelMed - LongCat Flash Lite
meituan-longcat/LongCat-Flash-Lite - MiniMax M1
MiniMax/MiniMax-M1-80k - MiniMax M3
MiniMax/MiniMax-M3 - Mistral Large
mistralai/Mistral-Large-Instruct-2407 - Qwen Image Edit
MusePublic/Qwen-Image-Edit - CompassJudger 32B
opencompass/CompassJudger-1-32B-Instruct - InternVL 3.5
OpenGVLab/InternVL3_5-241B-A28B - ERNIE 4.5 0.3B
PaddlePaddle/ERNIE-4.5-0.3B-PT - ERNIE 4.5 21B
PaddlePaddle/ERNIE-4.5-21B-A3B-PT - ERNIE 4.5 300B
PaddlePaddle/ERNIE-4.5-300B-A47B-PT - ERNIE 4.5 VL 28B
PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT - Qwen Image Edit
Qwen/Qwen-Image-Edit - Qwen 3 14B
Qwen/Qwen3-14B - Qwen 3 235B
Qwen/Qwen3-235B-A22B - Qwen 3 235B
Qwen/Qwen3-235B-A22B-Instruct-2507 - Qwen 3 235B Thinking
Qwen/Qwen3-235B-A22B-Thinking-2507 - Qwen 3 30B A3B
Qwen/Qwen3-30B-A3B - Qwen 3 30B A3B Thinking
Qwen/Qwen3-30B-A3B-Thinking-2507 - Qwen 3 4B
Qwen/Qwen3-4B - Qwen 3 8B
Qwen/Qwen3-8B - Qwen 3 Coder 30B
Qwen/Qwen3-Coder-30B-A3B-Instruct - Qwen 3 Embedding 0.6B
Qwen/Qwen3-Embedding-0.6B - Qwen 3 Embedding 4B
Qwen/Qwen3-Embedding-4B - Qwen 3 Embedding 8B
Qwen/Qwen3-Embedding-8B - Qwen 3 Next 80B
Qwen/Qwen3-Next-80B-A3B-Instruct - Qwen 3 Next 80B Thinking
Qwen/Qwen3-Next-80B-A3B-Thinking - Qwen 3 VL 235B
Qwen/Qwen3-VL-235B-A22B-Instruct - Qwen 3 VL 8B
Qwen/Qwen3-VL-8B-Instruct - Qwen 3 VL 8B Thinking
Qwen/Qwen3-VL-8B-Thinking - Qwen 3.5 122B
Qwen/Qwen3.5-122B-A10B - Qwen 3.5 27B
Qwen/Qwen3.5-27B - Qwen 3.5 35B
Qwen/Qwen3.5-35B-A3B - Qwen 3.5 397B
Qwen/Qwen3.5-397B-A17B - Qwen 3.8 27B
Qwen/Qwen3.8-27B - Qwen 3.8 Flash Next
Qwen/Qwen3.8-Flash-Next - Intern S1
Shanghai_AI_Laboratory/Intern-S1 - Intern S1 Mini
Shanghai_AI_Laboratory/Intern-S1-mini - Intern S2
Shanghai_AI_Laboratory/Intern-S2-Preview - Step 3.5 Flash
stepfun-ai/Step-3.5-Flash - Step 3.7 Flash
stepfun-ai/Step-3.7-Flash - Hunyuan Hy3
Tencent-Hunyuan/Hy3 - XiYanSQL 32B
XGenerationLab/XiYanSQL-QwenCoder-32B-2412 - XiYanSQL 32B 2504
XGenerationLab/XiYanSQL-QwenCoder-32B-2504 - GLM 4.7 Flash
ZhipuAI/GLM-4.7-Flash - GLM 5.2
ZhipuAI/GLM-5.2