Model prices / Alibaba / Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507Open weights
Alibaba · released 2025-07-25
No price from the maker itself is on record for Qwen3 235B A22B Thinking 2507. The lowest of 12 providers is NanoGPT: $0.3 per 1M input tokens and $0.5 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 81.9K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestqwen/ | $0.3 | $0.5 | — | Lowest | Official docs |
 submodelQwen/ | $0.2 | $0.6 | — | Official docs | |
EEden AIdeepinfra/ | $0.23 | $2.3 | $0.2 | Official docs | |
HHeliconeqwen3-235b-a22b-thinking | $0.3 | $2.9 | — | Official docs | |
 Hugging FaceQwen/ | $0.3 | $3 | — | Official docs | |
JJiekou.AIqwen/ | $0.3 | $3 | — | Official docs | |
KKilo Gatewayqwen/ | $0.45 | $3.5 | — | Official docs | |
 OpenRouterqwen/ | $0.45 | $3.5 | — | Official docs | |
 Venice AIqwen3-235b-a22b-thinking-2507 | $0.45 | $3.5 | — | Official docs | |
 IO.NETDeprecatedQwen/ | $0.11 | $0.6 | $0.055 | Deprecated | Official docs |
QQiniuDeprecatedqwen3-235b-a22b-thinking-2507 | $0.289855 | $2.898551 | — | Deprecated | Official docs |
 ModelScopeQwen/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Qwen reasoning model for deliberate problem solving, math, and coding
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 81.9K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2025-07-25
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.