qwen

Qwen: Qwen3 30B A3B

The Qwen 3 30B A3B model is designed for text input and processing, with a context length of up to 131,072 tokens. It supports both tools and reasoning capabilities, but does not provide structured output. This model can handle a wide range of text-based tasks. For those looking for a high-scoring model within budget, the Qwen 3 30B A3B may be worth considering. With input costs at $0.12 per million tokens and output costs at $0.5 per million tokens, this model's price point is competitive with its blended benchmark score of 20.6 across two independent benchmarks, including AI Index and EQ Bench scores of 12.4 and 36.7 respectively. However, it's essential to evaluate multiple models before making a final decision.

Open weights 30.5B parameters, about 17.0 GiB at Q4_K_M: fits comfortably on 4 of 18 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
91/100
price + capability + benchmarks
Input Price
$0.12
per 1M tokens · checked 2026-09-23
Output Price
$0.50
per 1M tokens · checked 2026-09-23
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 20.3 across 2 benchmarks, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 12.4
EQ-Bench emotional understanding in dialogue 36.7
Model ID
qwen/qwen3-30b-a3b
Vendor
qwen
Released
April 2025
Tokenizer
Qwen3
Input Modalities
text
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.12/M input and $0.50/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.08
A month of a busy support chatbot 5M in / 2M out $1.60

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-08-23 $0.12 $0.50 131,072
2026-08-16 $0.13 $0.52 131,072
2026-07-27 $0.12 $0.50 131,072
2026-07-18 $0.13 $0.52 131,072
2026-07-17 $0.12 $0.50 131,072

Similar models

Quick answers

How much does Qwen: Qwen3 30B A3B cost?
$0.12 per million input tokens and $0.50 per million output tokens.
What is Qwen: Qwen3 30B A3B's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Qwen: Qwen3 30B A3B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Qwen: Qwen3 30B A3B process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.