LLM Perks

Qwen2.5 72B

Alibaba Cloud · All Qwen models
Free right now Frontier
Tool useOpen weights

Qwen2.5 72B is a language model with 72B parameters from Alibaba Cloud. It is currently free at 1 provider with up to 131K tokens of context. The model supports tool calling. Its weights are open, so it can also run locally.

Developer
Alibaba Cloud
Parameters
72B
Context
131K tokens
Type
Text
License
Open weights

Where to use Qwen2.5 72B for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
Together AI
Qwen/Qwen2.5-72B
131K Fair use (depends on server load) — Open

Quick start

curl https://api.together.xyz/v1/chat/completions \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-72B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
7.7
GPQA Diamond
49.1%
Humanity's Last Exam
3.6%
Terminal-Bench Hard
4.5%
τ²-Bench
34.5%

Source: Artificial Analysis · Qwen2.5 Instruct 72B

Similar free models

FAQ

Is Qwen2.5 72B free?

Yes. As of October 31, 2026, Qwen2.5 72B is free at Together AI. Each provider has its own limits — see the table above.

What is the context window of Qwen2.5 72B?

The largest context among free routes is 131,072 tokens. Some providers cap it lower.

How do I call Qwen2.5 72B via API?

Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID Qwen/Qwen2.5-72B, and a Together AI key.

How good is Qwen2.5 72B?

Artificial Analysis Intelligence Index: 7.7, GPQA Diamond: 49%. For comparison, the strongest free model in the catalog right now is GLM 5.3 Flash.

Is Qwen2.5 72B open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.