All Models
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 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.
Benchmarks
Available Providers (12)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 ModelScope | Qwen/Qwen3-Coder-30B-A3B-Instruct | $0.00/MTok | $0.00/MTok | 262.1K | 65.5K | |
 NovitaAI | qwen/qwen3-coder-30b-a3b-instruct | $0.07/MTok | $0.27/MTok | 160K | 32.8K | |
 OpenRouter | qwen/qwen3-coder-30b-a3b-instruct | $0.07/MTok | $0.27/MTok | 160K | 65.5K | |
 OVHcloud AI Endpoints | qwen3-coder-30b-a3b-instruct | $0.07/MTok | $0.26/MTok | 262.1K | 262.1K | |
 Helicone | qwen3-coder-30b-a3b-instruct | $0.10/MTok | $0.30/MTok | 262.1K | 262.1K | |
 Nebius Token Factory | Qwen/Qwen3-Coder-30B-A3B-Instruct | $0.10/MTok | $0.30/MTok | 128K | 8.2K | |
 NanoGPT | qwen3-coder-30b-a3b-instruct | $0.10/MTok | $0.40/MTok | 128K | 65.5K | |
 Clarifai | qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct | $0.11/MTok | $0.75/MTok | 262.1K | 65.5K | |
 Amazon Bedrock | qwen.qwen3-coder-30b-a3b-v1:0 | $0.15/MTok | $0.60/MTok | 262.1K | 131.1K | |
 Scaleway | qwen3-coder-30b-a3b-instruct | $0.20/MTok | $0.80/MTok | 128K | 32.8K | |
 Alibaba (China) | qwen3-coder-30b-a3b-instruct | $0.22/MTok | $0.86/MTok | 262.1K | 65.5K | |
 Alibaba | qwen3-coder-30b-a3b-instruct | $0.45/MTok | $2.25/MTok | 262.1K | 65.5K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output