Qwen

Qwen: Qwen3 235B A22B Thinking 2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

ReasoningTool callingStreamingJSON mode
131.1K token context Released Jul 25, 2025

Intelligence overview

0
Intelligence
0
Coding
0
Agentic

131.1K tok

Context window

118.0K tok

Max output

Capabilities

What Qwen: Qwen3 235B A22B Thinking 2507 can do.

Reasoning

Extended reasoning

Works through problems step by step before answering, trading latency for accuracy on harder tasks.

Development

Tool calling

Calls external functions mid-response, then continues reasoning from the result.

Structured output

Returns responses constrained to a JSON schema, ready to parse without cleanup.

Streaming

Streams tokens as they're generated instead of waiting on the full response.

Performance

Intelligence12.7
Artificial Analysis
Coding22.1
Artificial Analysis
Agentic1.3
Artificial Analysis

Design Arena — ranked #100 across 6 categories

Pricing

Pay for what you use.

Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.

INPUT

$0.23 / 1M tok

OUTPUT

$2.3 / 1M tok

Use cases

Built for serious work.

Build

Generate and refactor code, with the ability to run and verify tool calls and return structured, parseable output.

Think

Works through multi-step problems with extended reasoning before it answers.

Research

Holds up to 131.1K tokens of source material in context without losing the thread.

Automate

Chains tool calls across multi-step workflows, reasoning between each one.

Preview

Ask Qwen: Qwen3 235B A22B Thinking 2507 anything.

A preview of the real UltraGPT composer — the model you see here is the model you get.

Qwen: Qwen3 235B A22B Thinking 2507 Ready

Continues in the UltraGPT app — one login, every model.

Comparison

How Qwen: Qwen3 235B A22B Thinking 2507 stacks up.

The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.

Specification

Technical details.

Specification

Context window
131.1K tokens
Max output
118.0K tokens
Input modalities
Text
Output modalities
Text
Knowledge cutoff
Jun 30, 2025
Release date
Jul 25, 2025
Streaming
Supported
Tool calling
Supported
JSON mode
Supported

Model identity

Provider
Qwen
Provider ID
qwen

Model ID

Directory

More from Qwen, and everything else.

This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.

Qwen: Qwen3 235B A22B Thinking 2507, one subscription away.

UltraGPT puts this model — and every other one in the directory — behind a single login and one flat monthly price.