Model information
Released
2025-07-28
Context window
1M
Max output
66K
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-coder-flash
- Knowledge cutoff
- 2025-04
- Aliases
- Qwen3 Coder Flash
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| LLM Gateway | qwen3-coder-flash | openai_chat | 1M | 66K | Tool callTemperature | - | input $0.3/M · output $1.5/M cache read $0.06/M · cache write $0.375/M | Yes | ||
| DigitalOcean | qwen3-coder-flash | openai_chat | 1M | 66K | Tool callTemperature | - | input $0.45/M · output $1.7/M cache read $0.09/M | Yes | ||
| Alibaba | qwen3-coder-flash | custom | 1M | 66K | Tool callTemperature | - | input $0.3/M · output $1.5/M | Yes | ||
| Alibaba (China) | qwen3-coder-flash | custom | 1M | 66K | Tool callTemperature | - | input $0.144/M · output $0.574/M | Yes | ||
| OpenRouter | qwen/qwen3-coder-flash | openai_chat | 1M | 66K | Tool callStructuredTemperature | - | input $0.195/M · output $0.975/M cache read $0.039/M · cache write $0.244/M | Yes | ||
| NanoGPT | qwen/qwen3-coder-flash | openai_chat | 1M | 66K | Temperature | - | input $0.3/M · output $1.5/M cache read $0.15/M | Yes | ||
| Kilo Gateway | qwen/qwen3-coder-flash | openai_chat | 1M | 66K | Tool callTemperature | - | input $0.195/M · output $0.975/M cache read $0.039/M · cache write $0.244/M | Yes | ||
| Merge Gateway | qwen/qwen3-coder-flash | openai_chat | 1M | 66K | Tool callTemperature | - | input $0.144/M · output $0.574/M cache read $0.029/M | Yes |