← All models
Qwen3 32B
qwen
Dense open Qwen model for self-hosted chat, reasoning, and coding
- Context
- 131,072
- Output
- 16,384
- Release date
- 2025-04
- Open weights
- Yes
⌘K
qwen
Dense open Qwen model for self-hosted chat, reasoning, and coding
| Provider | Model id | Context | Price | Status |
|---|---|---|---|---|
| Kilo Gateway | qwen/qwen3-32b | 40,960 | $0.08–$0.28 | — |
| Deep Infra | Qwen/Qwen3-32B | 40,960 | $0.08–$0.28 | — |
| OpenRouter | qwen/qwen3-32b | 131,072 | $0.08–$0.28 | — |
| Cortecs | qwen3-32b | 32,000 | $0.089–$0.312 | — |
| Abacus | Qwen/Qwen3-32B | 131,072 | $0.09–$0.29 | — |
| NanoGPT | qwen/qwen3-32b | 41,000 | $0.1–$0.3 | — |
| Chutes | Qwen/Qwen3-32B-TEE | 40,960 | $0.104–$0.416 | — |
| Amazon Bedrock | qwen.qwen3-32b-v1:0 | 32,768 | $0.15–$0.6 | — |
| Merge Gateway | qwen/qwen3-32b | 131,072 | $0.15–$0.6 | — |
| Hugging Face | Qwen/Qwen3-32B | 131,072 | $0.29–$0.59 | — |
| LLM Gateway | scx-ai/qwen3-32b | 32,768 | $0.36–$0.87 | — |
| DevPass (LLM Gateway) | qwen3-32b | 40,960 | $0.36–$0.87 | — |
| Alibaba | qwen3-32b | 131,072 | $0.7–$2.8 | — |
| Pioneer | Qwen/Qwen3-32B | 131,072 | $0.9–$0.9 | — |