All modelsCalculate what your real prompts cost on Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507
open sourceQwen model, released 25 Jul 2025.
$0.23
per 1M input tokens
$2.30
per 1M output tokens
—
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 31 Jul 2026
Specifications
- Lab
- Qwen
- Released
- 25 Jul 2025
- Context window
- 131k tokens
- Max output
- 118k tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- 2025-06-30
- Open source
- Yes
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1424.9 (1410.2–1439.6) | 13 Sept 2026 |
| LMArena (Chatbot Arena) | overall | 1415.1 (1408.5–1421.6) | 13 Sept 2026 |
LMArena (Chatbot Arena) data © their authors, CC-BY-4.0
Frequently asked questions
How much does Qwen3 235B A22B Thinking 2507 cost?
Qwen3 235B A22B Thinking 2507 costs $0.23 per 1M input tokens and $2.30 per 1M output tokens (list price, updated every 6 hours).
What is Qwen3 235B A22B Thinking 2507's context window?
Qwen3 235B A22B Thinking 2507 supports a 131k-token context window with up to 118k output tokens.