Qwen

Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Qwen3 235B A22B Thinking 2507

reasoning open weights tools

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...

Input $/1M: $0.23
Output $/1M: $2.30
Context: 131K
Max output: 118K
Released: Jul 25, 2025
Modalities: text

Intelligence index-

Coding index22

Agentic index-

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Qwen3 235B A22B Thinking 2507
targets:
  - id: qwen3-235b-a22b-thinking-2507
    kind: llm
    name: Qwen3 235B A22B Thinking 2507
    metadata:
      model: qwen/qwen3-235b-a22b-thinking-2507          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.001265

Price among Qwen models

Input list price per million tokens; Qwen3 235B A22B Thinking 2507 is the 5th cheapest of 13 listed.

1
Qwen3.7 Flash
$0.03
2
Qwen3.6 35B A3B
$0.10
3
Qwen3.8 Flash
$0.15
4
Qwen3.6 Flash
$0.19
5
Qwen3 235B A22B Thinking 2507
$0.23
6
Qwen3.5 Plus 2026-04-20
$0.30
7
Qwen3.7 Plus
$0.32
8
Qwen3.8 27B
$0.42
9
Qwen3.6 Max Preview
$1.03
10
Qwen3.7 Max
$1.48
11
Qwen3.8 Max (0902)
$2.00
12
Qwen3.8 2.4T A95B
$2.00

More from Qwen

Other models by the same vendor in the catalogue.