Qwen3 30B A3B API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen3 30B A3B. Find the best value for your use case.

Sponsor Price Per Token— Reach 5000+ developers comparing LLM APIs

124 out of our 298 tracked models have had a price change in January.

Get our weekly newsletter on pricing changes, new releases, and tools.

Last updated: January 22, 2026 at 08:06 AM

Overview

Qwen3 30B A3B was released on April 28, 2025. Pricing starts at $0.060 per million input tokens and $0.220 per million output tokens. The model supports a context window of up to 41K tokens. API access is available through Qwen.

Context Window

41K

tokens

Pricing

Input$0.060

Output$0.220

per 1M tokens

Speed

Output62 tok/s

TTFT1.07s

median latency

Capabilities

Tools

Pricing Comparison

Compare Qwen3 30B A3B with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Coding	MMLU	GPQA	Context	Actions
QW Qwen	Qwen3 30B A3B	$0.060	$0.220	32.2	71.0	51.5	40,960	Try
MI Mistral AI	Devstral 2 2512	$0.050	$0.220	44.8	76.2	59.4	262,144	Try
O OpenAI	GPT-5 Nano	$0.050	$0.400	78.9	78.0	67.6	400,000	Try
Z Z-ai	GLM 4.5 Air	$0.050	$0.220	68.4	81.5	73.3	131,072	Try
QW Qwen	Qwen3 14B	$0.050	$0.220	28.0	67.5	47.0	40,960	Try
QW Qwen	Qwen2.5 VL 32B Instruct	$0.050	$0.220	24.8	69.7	46.6	16,384	Try
QW Qwen	Qwen-Turbo	$0.050	$0.200	16.3	63.3	41.0	1,000,000	Try
QW Qwen	Qwen3 8B	$0.050	$0.250	20.2	64.3	45.2	32,000	Try
QW Qwen	Qwen3 30B A3B Thinking 2507	$0.051	$0.340	—	—	—	32,768	Try
NV Nvidia	Nemotron 3 Nano 30B A3B	$0.060	$0.240	36.0	57.9	39.9	262,144	Try
MI Mistral AI	Mistral Small 3.2 24B	$0.060	$0.180	27.5	68.1	50.5	131,072	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Qwen3 30B A3B is available from multiple providers with different pricing and availability.

Providers

$0.060

Cheapest Input/M

$0.220

Cheapest Output/M

Chutes

Best Price

Provider Pricing

7 models

Provider	Input $/M	Output $/M	Uptime
C Chutes Best Price	$0.060	$0.220	82.0%
N NCompass	$0.080	$0.280	98.1%
D DeepInfra	$0.080	$0.290	100.0%
S SiliconFlow	$0.090	$0.450	95.7%
N Novita	$0.090	$0.450	99.7%
N NextBit	$0.140	$0.550	100.0%
F Friendli	$0.150	$0.600	-

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare Qwen3 30B A3B's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

Qwen3 30B A3B

Qwen3 30B A3B (Thinking)

Other models

Detailed Benchmark Scores

Benchmark	Standard	Thinking
Intelligence	12.4 (15th)	15.8 (8th)
Coding	13.3 (33th)	11.0 (11th)
Math	21.7 (23th)	72.3 (26th)
MMLU Pro	71.0 (35th)	77.7 (16th)
GPQA	51.5 (33th)	61.6 (11th)
LiveCodeBench	32.2 (33th)	50.6 (8th)
AIME	26.0 (45th)	75.3 (27th)
Aider	-	-

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Qwen3 30B A3B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Qwen3 30B A3B directly in your browser.

Open Playground

Compare Qwen3 30B A3B

Frequently Asked Questions

All Qwen Models

See pricing for all Qwen models.

View all Qwen models →