What this model supports
ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
- Creator
- Alibaba Qwen
- Family
- qwen
- Modalities
- Text
- License
- Not documented
- Release date
- 2025-04
- Model ID
alibaba/qwen3-32b
Qwen3 32B
alibaba/qwen3-32bDense open Qwen model for self-hosted chat, reasoning, and coding
Input modalities
Output modalities
Source-linkedqwenOpen weightsReleased 2025-04
Context window131.072K
Maximum output16.384K
Provider offers11
Knowledge cutoff2025-04
Market availability
Report price →Provider pricing
| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 OpenRouter | qwen/qwen3-32b | 131.072K | $0.08 | $0.28 | — | R T S | View{
"input": 0.08,
"output": 0.28
} |
 Deep Infra | Qwen/Qwen3-32B | 40.96K | $0.08 | $0.28 | — | R T S | View{
"input": 0.08,
"output": 0.28
} |
 Abacus | Qwen/Qwen3-32B | 131.072K | $0.09 | $0.29 | — | R T · | View{
"input": 0.09,
"output": 0.29
} |
 Cortecs | qwen3-32b | 16.384K | $0.099 | $0.33 | — | · T · | View{
"input": 0.099,
"output": 0.33
} |
 Jiekou.AI | qwen/qwen3-32b-fp8 | 40.96K | $0.1 | $0.45 | — | R · · | View{
"input": 0.1,
"output": 0.45
} |
 LLM Gateway | qwen3-32b | 32.768K | $0.1 | $0.3 | — | R T · | View{
"input": 0.1,
"output": 0.3,
"reasoning": 8.4
} |
 Alibaba (China) | qwen3-32b | 131.072K | $0.287 | $1.147 | — | R T · | View{
"input": 0.287,
"output": 1.147,
"reasoning": 2.868
} |
 Hugging Face | Qwen/Qwen3-32B | 131.072K | $0.29 | $0.59 | — | R T S | View{
"input": 0.29,
"output": 0.59
} |
 Helicone | qwen3-32b | 131.072K | $0.29 | $0.59 | — | R T · | View{
"input": 0.29,
"output": 0.59
} |
 Alibaba | qwen3-32b | 131.072K | $0.7 | $2.8 | — | R T · | View{
"input": 0.7,
"output": 2.8,
"reasoning": 8.4
} |
 Pioneer | Qwen/Qwen3-32B | 131.072K | $0.9 | $0.9 | $0.9 | R T · | View{
"cache_read": 0.9,
"cache_write": 0.9,
"input": 0.9,
"output": 0.9
} |
Published benchmark results
Aider Polyglot
vs top 8 models