Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
ReasoningToolsJSON
Intelligence
—
Design Elo
1077
Website
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.300
145th cheapest
Context
262K
33K max out
How it compares
Cheaper than57%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaDesign Arena · Elo4,934 tournaments
Website
1077
3D
1056
Data Viz
976
Providers & pricing (4)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.230 | $2.30 | 262K | 100% |
| Alibabafp8 | $0.230 | $2.30 | 131K | 100% |
| Novitafp8 | $0.300 | $3.00 | 131K | — |
| Venicefp8 | $0.450 | $3.50 | 128K | — |
Specifications
Context window262K
Max output33K
Knowledge cutoffJun 2025
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3-235B-A22B-Thinking-2507 ↗
Qwen3 235B A22B Thinking 2507 FAQ
How much does Qwen3 235B A22B Thinking 2507 cost?
Qwen3 235B A22B Thinking 2507 costs $0.300 per million input tokens and $3.00 per million output tokens via OpenRouter, making it 145th cheapest of 335 paid models.
What is Qwen3 235B A22B Thinking 2507's context window?
Qwen3 235B A22B Thinking 2507 supports a 262K-token context window and can output up to 33K tokens. It accepts text input.
More from qwen
All Qwen3 235B A22B Thinking 2507 alternatives →Compare head-to-head
Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.7 FlashQwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.7 PlusQwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.7 MaxQwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.5 Plus 2026-04-20Qwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.6 FlashQwen: Qwen3 235B A22B Thinking 2507 vs Qwen: Qwen3.6 35B A3B