LLM Perks

Qwen3 235B

Alibaba Cloud · All Qwen models
Free right now Frontier
ReasoningCodingTool useLong contextOpen weights

Qwen3 235B is a language model with 235B parameters from Alibaba Cloud. It is currently free at 1 provider with up to 262K tokens of context. The model supports step-by-step reasoning, is suited to coding, supports tool calling. Its weights are open, so it can also run locally.

Developer
Alibaba Cloud
Parameters
235B / 22B active
Context
262K tokens
Type
Text
License
Open weights

Where to use Qwen3 235B for free

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

ProviderContextLimitCard
Together AI
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8
262K 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/Qwen3-235B-A22B-Instruct-2507-FP8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

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

Benchmarks

Intelligence Index
12.7
GPQA Diamond
79.0%
Humanity's Last Exam
15.9%
Terminal-Bench Hard
13.6%
τ²-Bench
53.2%
Long context (LCR)
72.0%

Source: Artificial Analysis · Qwen3 235B A22B 2507 (Reasoning)

Similar free models

FAQ

Is Qwen3 235B free?

Yes. As of October 29, 2026, Qwen3 235B is free at Together AI. Each provider has its own limits — see the table above.

What is the context window of Qwen3 235B?

The largest context among free routes is 262,144 tokens. Some providers cap it lower.

How do I call Qwen3 235B via API?

Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID Qwen/Qwen3-235B-A22B-Instruct-2507-FP8, and a Together AI key.

How good is Qwen3 235B?

Artificial Analysis Intelligence Index: 12.7, GPQA Diamond: 79%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Qwen3 235B open-weight?

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