Qwen
Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
Score48
Add to CompareInput / M
Output / M
Context
Max Output
Unavailable
Usage
Unranked
Quality
28.1 / 100
Providers
3
Best Uptime 30m
100.00%
Released
Jul 25, 2025
Modalities
text
About
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...
Capabilities
Vision
Tools
Reasoning
Streaming
JSON Mode
Providers · 3
Per-provider pricing, uptime
| Provider | Input/M | Output/M | Context | Max Out | Quant | Uptime 30m |
|---|---|---|---|---|---|---|
| AlibabaRecommended Alibaba | qwen/qwen3-235b-a22b-thinking-2507 | $0.150 | $1.50 | 131K | — | unknown | 100.00% |
| Novita Novita | qwen/qwen3-235b-a22b-thinking-2507 | $0.300 | $3.00 | 131K | 33K | fp8 | 98.77% |
| DeepInfra DeepInfra | qwen/qwen3-235b-a22b-thinking-2507 | $0.230 | $2.30 | 262K | 33K | fp8 | 97.59% |
Benchmarks
Quality index 28.1 / 100
Artificial Analysis
intelligence index
19.6 / 100
coding index
22.1 / 100
agentic index
3.80 / 100
Design Arena
elo models website
1095.0
elo models codecategories
1082.0
elo models 3d
1077.0
elo models gamedev
1023.0
elo models uicomponent
996.0
elo models dataviz
991.0
Performance History
51 snapshots
Price History
1 recorded changes
Activity Timeline
- 3d agoprice changedInput price $0.100 → $0.150
Versus
Nearest peers by price, context, and capabilities. One click to compare.
No comparable models found.
First seen 3d ago · Last verified 3m ago