Qwen3.5 122B-A10BOpen weights
Alibaba · released 2026-02-23
The official API price of Qwen3.5 122B-A10B is $0.4 per 1M input tokens and $3.2 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 22 providers sell it. The lowest is AIHubMix: $0.1126 input, $0.9008 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| $0.4 | $3.2 | — | Official | Official docs | |
| $0.1126 | $0.9008 | — | LowestTiered pricing | Official docs | |
| $0.115 | $0.917 | $0.115 | Tiered pricing | Official docs | |
MMerge Gatewayqwen/ | $0.115 | $0.917 | $0.023 | Official docs | |
OOrcaRouterTiered pricingqwen/ | $0.115 | $0.917 | — | Tiered pricing | Official docs |
| $0.119558 | $0.956464 | — | Tiered pricing | Official docs | |
KKilo Gatewayqwen/ | $0.26 | $2.08 | — | Official docs | |
NNanoGPTqwen/ | $0.26 | $2.08 | $0.103788 | Official docs | |
NNanoGPTqwen/ | $0.26 | $2.08 | $0.103788 | Official docs | |
| $0.26 | $2.08 | — | Official docs | ||
| $0.26 | $2.08 | — | Official docs | ||
NNeonqwen35-122b-a10b | $0.22 | $2.2 | — | Official docs |
13 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
OOfoxbailian/ | $0.29 | $2.29 | $0.29 | Official docs | |
OOfoxqwen/ | $0.29 | $2.29 | $0.29 | Official docs | |
| $0.4 | $3.2 | — | Official docs | ||
JJalapeno CloudQwen3.5-122B-A10B | $0.4 | $3.2 | — | Official docs | |
| $0.4 | $3.2 | — | Official docs | ||
LLLM Gatewayalibaba/ | $0.4 | $3.2 | — | Official docs | |
LLLM Gatewaynovita/ | $0.4 | $3.2 | — | Official docs | |
MMixlayerqwen/ | $0.4 | $3.2 | — | Official docs | |
| $0.4 | $3.2 | — | Official docs | ||
RRegolo AIqwen3.5-122b | $1.1215 | $4.7103 | — | Official docs | |
| $0.29 | $2.4 | — | Deprecated | Official docs | |
TTensorXDeprecatedqwen/ | $0.5 | $3.5 | $0.125 | Deprecated | Official docs |
IInfomaniakDeprecatedQwen/ | $0.5 | $3.97 | — | Deprecated | 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 vision-language model for visual reasoning, documents, and agent tasks
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 65.5K
- Input
- Text, Image, Video
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2026-02-23
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.