Qwen3-Next 80B-A3B InstructDeprecatedOpen weights
Alibaba · released 2025-09
The official API price of Qwen3-Next 80B-A3B Instruct is $0.5 per 1M input tokens and $2 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 32.8K output tokens per request. 18 providers sell it. The lowest is Deep Infra: $0.09 input, $1.1 output. This model is marked as deprecated.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialDeprecatedqwen3-next-80b-a3b-instruct | $0.5 | $2 | — | OfficialDeprecated | Official docs |
 Deep InfraLowestQwen/ | $0.09 | $1.1 | — | Lowest | Official docs |
EEden AIdeepinfra/ | $0.09 | $1.1 | — | Official docs | |
KKilo Gatewayqwen/ | $0.09 | $1.1 | — | Official docs | |
NNanoGPTqwen/ | $0.09 | $1.1 | $0.07 | Official docs | |
 OpenRouterqwen/ | $0.09 | $1.1 | — | Official docs | |
MMerge Gatewayqwen/ | $0.1 | $1.1 | $0.05 | Official docs | |
 Hugging FaceQwen/ | $0.25 | $1 | — | Official docs | |
 Amazon Bedrockqwen. | $0.15 | $1.2 | — | Official docs | |
NNeonqwen3-next-80b-a3b-instruct | $0.15 | $1.2 | — | Official docs | |
 Vercel AI Gatewayalibaba/ | $0.15 | $1.2 | — | Official docs | |
EEden AIdatabricks/ | $0.15001 | $1.20001 | $0.015001 | Official docs |
8 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
EEden AIdatabricks/ | $0.15001 | $1.20001 | $0.015001 | Official docs | |
 IO.NETQwen/ | $0.11875 | $1.2625 | $0.059375 | Official docs | |
 AI/ML APIalibaba/ | $0.1587 | $1.2696 | — | Official docs | |
HHeliconeqwen3-next-80b-a3b-instruct | $0.14 | $1.4 | — | Official docs | |
JJiekou.AIqwen/ | $0.15 | $1.5 | — | Official docs | |
 Venice AIqwen3-next-80b | $0.35 | $1.9 | — | Official docs | |
QQiniuDeprecatedqwen3-next-80b-a3b-instruct | $0.144928 | $0.57971 | — | Deprecated | Official docs |
JJalapeno CloudDeprecatedQwen3-Next-80B-A3B-Instruct | $0.15 | $1.5 | — | 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 instruction model for multilingual chat, reasoning, and tool use
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 32.8K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2025-09
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.