Qwen3 235B A22B Thinking 2507
alibaba/qwen3-235b-a22b-thinking-2507Qwen reasoning model for deliberate problem solving, math, and coding
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...
Context
262K
262,144 tokens
Max output
82K
81,920 tokens
Input
$0.30
per 1M tokens
Output
$3.00
per 1M tokens
Providers
13
13 listings
Intelligence
12.7
Intelligence Index
Pricing
USD per 1M tokens · listed by Hugging Face
| Token type | Standard |
|---|---|
| Input | $0.30 |
| Output | $3.00 |
Lowest input price across providers: Free.
Capabilities
ReasoningYes
Effort: low, medium, high
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningYes
Field: reasoning_content
Open weightsYes
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence12.7#136 of 208
- Coding22.1#91 of 112
- Agentic1.3#71 of 86
- Arena987#115 of 128
Rankings
Position on each OneAtlas leaderboard
Providers · 13
13 listings
Hugging Face
NanoGPT
LLM Gateway
Kilo Gateway
Eden AI
DevPass (LLM Gateway)
Venice AI
Helicone
Qiniu
Jiekou.AI
IO.NET
submodel
ModelScope| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DevPass (LLM Gateway) | qwen3-235b-a22b-thinking-2507 | 262K | — | 8K | $0.30 | $3.00 | — | — | — | — | — | Yes | Yes | Yes | Yes | Jul 8, 2025 |
| Eden AI | deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | — | 82K | $0.23 | $2.30 | — | $0.20 | — | — | — | Yes | Yes | Yes | Yes | Jul 25, 2025 |
| Helicone | qwen3-235b-a22b-thinking | 262K | — | 82K | $0.30 | $2.90 | — | — | — | — | — | Yes | No | Unknown | Yes | Jul 25, 2025 |
| Hugging Face | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | — | 82K | $0.30 | $3.00 | — | — | — | — | — | Yes | Yes | Unknown | Yes | Jul 25, 2025 |
| IO.NET | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | — | 4K | $0.11 | $0.60 | — | $0.06 | $0.22 | — | — | Yes | Yes | Unknown | Yes | Jul 25, 2025 |
| Jiekou.AI | qwen/qwen3-235b-a22b-thinking-2507 | 131K | — | 131K | $0.30 | $3.00 | — | — | — | — | — | Yes | Yes | Yes | Yes | Jul 25, 2025 |
| Kilo Gateway | qwen/qwen3-235b-a22b-thinking-2507 | 128K | — | 16K | $0.45 | $3.50 | — | — | — | — | — | Yes | Yes | No | Yes | Jul 25, 2025 |
| LLM Gateway | novita/qwen3-235b-a22b-thinking-2507 | 131K | — | 33K | $0.30 | $3.00 | — | — | — | — | — | No | Yes | No | Yes | Jul 25, 2025 |
| ModelScope | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | — | 131K | Free | Free | — | — | — | — | — | Yes | Yes | Unknown | Yes | Jul 25, 2025 |
| NanoGPT | qwen/qwen3-235b-a22b-thinking-2507 | 131K | 131K | 82K | $0.30 | $0.50 | — | — | — | — | — | No | Yes | No | Yes | Jul 25, 2025 |
| Qiniu | qwen3-235b-a22b-thinking-2507 | 262K | — | 4K | $0.29 | $2.90 | — | — | — | — | — | Yes | Yes | Yes | Yes | Jul 25, 2025 |
| submodel | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | — | 131K | $0.20 | $0.60 | — | — | — | — | — | Yes | Yes | Unknown | Yes | Jul 25, 2025 |
| Venice AI | qwen3-235b-a22b-thinking-2507 | 128K | — | 16K | $0.45 | $3.50 | — | — | — | — | — | Yes | Yes | Yes | Yes | Jul 25, 2025 |