Skip to content
LLMs
Qwen logo

Qwen: Qwen3 235B A22B Thinking 2507

by Qwen

Qwen: Qwen3 235B A22B Thinking 2507 is a large language model from Qwen. It costs $0.230 per million input tokens and $2.30 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputOpen weights
Input / 1M tokens
$0.230
Output / 1M tokens
$2.30
Cached input / 1M
-

Not supported

Context window
131K

tokens

Who serves it cheapest

3 hosts serve Qwen3 235B A22B Thinking 2507. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen3 235B A22B Thinking 2507, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AlibabaCheapest$0.230$2.30131K-100.0%
Novitafp8$0.300$3.00131K-99.9%
Venicefp8$0.450$3.50128K-99.9%

The spread between Alibaba and Venice is 1.6× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
12.7
Coding index
22.1
Agentic index
1.3

About 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...

Specifications

Qwen: Qwen3 235B A22B Thinking 2507 specifications
Model IDqwen/qwen3-235b-a22b-thinking-2507
ProviderQwen
Context window131K tokens
Max output118K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2025-06-30
Open weightsYes - Qwen/Qwen3-235B-A22B-Thinking-2507
ReleasedJuly 25, 2025

Cheaper alternatives

Models that cost less than Qwen3 235B A22B Thinking 2507 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Qwen: Qwen3 235B A22B Thinking 2507 cost?

$0.230 per million input tokens and $2.30 per million output tokens.

What is the context window of Qwen: Qwen3 235B A22B Thinking 2507?

131K tokens, with up to 118K tokens of output per request.

Which provider serves Qwen: Qwen3 235B A22B Thinking 2507 cheapest?

Alibaba at $0.230 per million input tokens - 1.6× cheaper than Venice, the most expensive of the 3 hosts serving it.

Confirm against the source: Qwen official pricing.