ZMIME
Alibaba (Qwen) · Released Apr 28, 2025

Qwen3 30B A3B

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning.

  • Open weights
  • Reasoning
  • Tool calling
Capability
134.2ECI · #129 of 158
Input
$0.109per 1M tokens
Output
$0.50per 1M tokens
Context
131K16K max output
Pricing

What it costs

Input
$0.109per million tokens
Output
$0.50per million tokens
Blended (3:1)
$0.206cheaper than 75% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.467
Team assistant25M input + 5M output tokens$5.22
Production app250M input + 50M output tokens$52.17

Median of 15 paid API providers on models.dev.

Capability

Independent benchmarks

134.2Epoch Capabilities Index
#129 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (131.5–136.8); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions61.7%
  • OTIS Mock AIME 2024–2025Competition mathematics62.8%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Apr 28, 2025
Context window
131,072 tokens
Max output
16,384 tokens
Inputs
Text
Output
Text
Reasoning
Always on
Tool calling
Yes
Structured output
No
Availability
15 API providerslisted on models.dev
Same lab

More from Alibaba (Qwen)

Questions

About Qwen3 30B A3B

How much does Qwen3 30B A3B cost?

Qwen3 30B A3B costs $0.109 input / $0.50 output per million tokens (median across 15 API providers). At a 3:1 input-to-output mix that is $0.206 per million tokens, cheaper than 75% of the 469 priced models we track.

What is the context window of Qwen3 30B A3B?

Qwen3 30B A3B accepts up to 131,072 tokens per request and can write up to 16,384 tokens in one response.

How good is Qwen3 30B A3B?

Epoch AI gives Qwen3 30B A3B a Capabilities Index score of 134.2 (likely range 131.5–136.8), ranking it #129 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 61.7%, OTIS Mock AIME 2024–2025 62.8%.

Is Qwen3 30B A3B open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen3 30B A3B support?

Qwen3 30B A3B accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Qwen3 30B A3B released?

Alibaba (Qwen) released Qwen3 30B A3B on Apr 28, 2025.

What are the best alternatives to Qwen3 30B A3B?

The closest current models from other labs on capability, price and release date are Gemini 2.0 Flash (Google, ECI 134.0, $0.10 / $0.42), Llama 4 Maverick 17B Instruct (Meta, ECI 132.2, $0.27 / $0.86), DeepSeek V3 0324 (DeepSeek, ECI 135.3, $0.275 / $1.12) and GPT-4.1 mini (OpenAI, ECI 134.3, $0.40 / $1.60).