Qwen: Qwen3 30B A3B

Public pricingIntelligence 72/100Medium memoryRéflexion approfondieOutils

Qwen: Qwen3 30B A3B est un modèle texte conçu pour raisonnement, planification et automatisation. Il associe une utilisation fiable des outils et des agents et un raisonnement et une planification poussés, un contexte de 41K tokens et un profil à faible coût pour un travail fiable sur reasoning, planning, and multi-step automation.

Input

$0.08/1M

Output

$0.28/1M

Cached

$0.03/1M

Batch

$0.05/1M

Calculate your Qwen3 30B A3B bill.

Set your workload — see cost at your exact volume.

What would Qwen3 30B A3B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Qwen3 30B A3B at a glance.

Memory

40,960

tokens

Max reply

40,960

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

qwen3

Released

Apr 2025

Training cutoff

Jan 2025

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • aime_2024

    80.4

  • gpqa_diamond

    43.9

  • mmlu

    81.4

  • mmlu_pro

    61.5

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Qwen3 30B A3B

  • Multi-step reasoning, research agents, or hard math.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Qwen3 30B A3B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Qwen3 30B A3B costs roughly $17 per month. Input is $0.08 /1M tokens and output is $0.28 /1M tokens.
Qwen3 30B A3B has a 40,960-token context window (medium memory — a long report or a codebase file). That means you can fit about 7,680 words of input and history in a single call.
Beyond text generation, Qwen3 30B A3B supports deep step-by-step reasoning, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Qwen3 30B A3B was released in April 2025, with training data cut off around January 2025.
Models in a similar class include Qwen3 30B A3B Thinking 2507, Qwen3 32B, Qwen3.5-Flash. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Qwen3 30B A3B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard