Qwen3 32BDeprecatedOpen weights
Alibaba · released 2025-04
The official API price of Qwen3 32B is $0.7 per 1M input tokens and $2.8 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 16.4K output tokens per request. 19 providers sell it. The lowest is NanoGPT: $0.08 input, $0.24 output. This model is marked as deprecated.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialDeprecatedqwen3-32b | $0.7 | $2.8 | — | OfficialDeprecated | Official docs |
NNanoGPTLowestqwen/ | $0.08 | $0.24 | $0.05 | Lowest | Official docs |
AAbacusQwen/ | $0.08 | $0.28 | — | Official docs | |
 Deep InfraQwen/ | $0.08 | $0.28 | — | Official docs | |
KKilo Gatewayqwen/ | $0.08 | $0.28 | — | Official docs | |
 OpenRouterqwen/ | $0.08 | $0.28 | — | Official docs | |
JJiekou.AIqwen/ | $0.1 | $0.45 | — | Official docs | |
 SiliconFlowQwen/ | $0.14 | $0.57 | — | Official docs | |
| SiliconFlow (China)Qwen/ | $0.149447 | $0.59779 | — | Official docs | |
 Amazon Bedrockqwen. | $0.15 | $0.6 | — | Official docs | |
MMerge Gatewayqwen/ | $0.15 | $0.6 | — | Official docs | |
 Vercel AI Gatewayalibaba/ | $0.15 | $0.6 | — | Official docs |
7 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
CCortecsqwen3-32b | $0.179 | $0.697 | — | Official docs | |
HHeliconeqwen3-32b | $0.29 | $0.59 | — | Official docs | |
 Hugging FaceQwen/ | $0.29 | $0.59 | — | Official docs | |
 DevPass (LLM Gateway)qwen3-32b | $0.36 | $0.87 | — | Official docs | |
LLLM Gatewayscx-ai/ | $0.36 | $0.87 | — | Official docs | |
QQiniuDeprecatedqwen3-32b | $0.289855 | $1.15942 | — | Deprecated | Official docs |
 PoeDeprecatedcerebras/ | — | — | — | 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
Dense open Qwen model for self-hosted chat, reasoning, and coding
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 16.4K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2025-04
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.