SF·SIX / MODEL PROFILE
Qwen3 Coder 30B A3B Instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Qwen3 Coder 30B A3B Instruct costs $0.07 per 1M input tokens and $0.28 per 1M output tokens at the standard tier, the lowest default-region price among the 2 providers SF·SIX tracks, from SiliconFlow (fp8). Updated ; prices checked .
- Developer
- Qwen (Alibaba)
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 262,144
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.07 input / $0.28 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| SiliconFlowOpenRouter | $0.07 | $0.28 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Amazon BedrockOpenRouter · us-west-2 region | $0.15 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.