AlibabaQwenTool use

Qwen3 Coder 30B A3B Instruct pricing

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 “think. This page tracks 3 listings in total. Highlighted lows are $0.070 per million input and $0.270 per million output (see table for which seller matches each).

262K context·3 providers·verified Apr 7, 2026
Best input$0.070per 1M tokens · Openrouter
Best output$0.270per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 3 offers are listed for Qwen3 Coder 30B A3B Instruct. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.070
Output / 1M
$0.270
N
Novita
Input / 1M
$0.070
Output / 1M
$0.270
FA
Fireworks AI
Input / 1M
$0.150
Output / 1M
$0.600

Input vs output · per provider

Cost calculator

Use this block to stress test Qwen3 Coder 30B A3B Instruct cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.070/M·Out: $0.270/M

0.007000¢ / req

0.013500¢ / req

Daily
$2.05
Monthly
$61
Annual
$748

Model specifications

Context length, caps, and capability flags for Qwen3 Coder 30B A3B Instruct. Family: Qwen. Values follow the main provider (Alibaba) record in our index.

Context window
262,144 tokens
Max output
262,144 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Jul 2025
Primary provider
Alibaba
Model family
Qwen

Compare Qwen3 Coder 30B A3B Instruct

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Qwen3 Coder 30B A3B Instruct.

Frequently asked questions

Read these after the table if you want plain language around Qwen3 Coder 30B A3B Instruct rates. The short model note from our index: 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. ...

Yes. Qwen3 Coder 30B A3B Instruct is available on Openrouter, Novita, Fireworks AI.

Also from Alibaba

Other models by Alibaba with live pricing in our catalog.