Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
- context
- 262K
- modalities
- text → text
- capabilities
- Tool use, Structured output, Low cost
Overview
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...
Providers
- AlibabaView Alibaba
- Amazon BedrockView Amazon Bedrock
- NovitaView Novita
- SiliconFlowView SiliconFlow
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.2925 | $1.4625 |
| Amazon Bedrock | $0.15 | $0.60 |
| Novita | $0.07 | $0.27 |
| SiliconFlow | $0.07 | $0.28 |
Alibaba
- input / 1M
- $0.2925
- output / 1M
- $1.4625
Amazon Bedrock
- input / 1M
- $0.15
- output / 1M
- $0.60
Novita
- input / 1M
- $0.07
- output / 1M
- $0.27
SiliconFlow
- input / 1M
- $0.07
- output / 1M
- $0.28
Use this model
through Nautili
Route requests to Qwen3 Coder 30B A3B Instruct through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.