Qwen3 30B A3B

Provider: Alibaba (Qwen) CN

Input price
$0.096
/ 1M tokens
Output price
$0.40
/ 1M tokens
Context
41K tokens
Max output 16K tokens

Overview

Alibaba's Qwen3 30B A3B is a mid-tier reasoning model built for agent tasks and multilingual workloads. Third-party hosting prices average $0.096 per million input tokens and $0.4 per million output tokens.

Strengths

  • Native support for function-calling and json-mode
  • Built-in thinking capabilities for reasoning
  • Knowledge cutoff date of 2025-03-31
  • Supports 40960 token context windows

Best use cases

  • Structured data extraction pipelines
  • Multilingual agent workflow execution
  • Complex reasoning tasks needing json output

Pricing position

Input cost matches Qwen3 Next 80B A3B ($0.09/M), but output pricing at $0.4/M exceeds the 80B variant's $1.1/M scale differently, matching GPT-4.1 Nano on output.

Caveats

Context window is limited to 40960 tokens, significantly smaller than sibling models exceeding 200k context.

Notes drafted by an LLM from the figures on this page (2026-11-15) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
16K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-04-28
Tracked since
2026-05-08
Last updated
2026-11-15

Features

Function callingJSON outputReasoning

Price history

  • 2026-11-15 Price change $0.12 / $0.50 → $0.096 / $0.40

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.03
1M (small app) 1 0.5 $0.30
10M (mid scale) 10 5 $2.96
100M (large) 100 50 $29.60

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-30b-a3b)