AI Observatory / Model Radar
Qwen / qwen/qwen3-coder-30b-a3b-instruct
Qwen: 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...
160,000
Context
32,768
Max output
$0.07 / 1M
Prompt price
2025-07-31
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Qwen | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.07 / 1M |
| Completion price | $0.27 / 1M | Request price | N/A |
| Context length | 160,000 | Max completion tokens | 32,768 |
| Supported parameters | frequency_penalty, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p | ||
Best for
qwen/qwen3-coder-30b-a3b-instruct
Qwen: 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...
Coding workflows
High-volume usage
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.