Qwen3 30B A3B

Qwen/Qwen3-30B-A3B · rates as of 2026-09-20 · Benchmarks · AI plans · Calculator

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

Cheapest input

$0.08

$/MTok · models.dev

Cheapest output

$0.29

$/MTok

Context

131K

tokens

Sources

16 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

Source	Provider	Input	Output	Cache read	Context
models.devcheapestqwen3-30b-a3b	Helicone	$0.08	$0.29	$0	41K
LiteLLMpinstripes/ps/qwen3-30b-a3b	N/A	$0.09	$0.2	$0.009	N/A
LiteLLMps/qwen3-30b-a3b	N/A	$0.09	$0.2	$0.009	N/A
models.devqwen/qwen3-30b-a3b	NanoGPT	$0.1	$0.3	$0.05	41K
LiteLLMnebius/Qwen/Qwen3-30B-A3B	N/A	$0.1	$0.3	$0.01	N/A
models.devqwen/qwen3-30b-a3b	Merge Gateway	$0.108	$1.08	$0.0216	131K
models.devqwen3-30b-a3b	302.AI	$0.11	$1.08	$0	128K
models.devQwen/Qwen3-30B-A3B	DeepInfra	$0.12	$0.5	$0.012	41K
models.devQwen/Qwen3-30B-A3B	Hugging Face	$0.12	$0.5	$0	41K
OpenRouterqwen/qwen3-30b-a3b	OpenRouter	$0.12	$0.5	$0.012	131K
LiteLLMQwen/Qwen3-30B-A3B	N/A	$0.12	$0.5	$0.012	N/A
LiteLLMQwen3-30B-A3B	N/A	$0.12	$0.5	$0.012	N/A
models.devqwen/qwen3-30b-a3b	Kilo Gateway	$0.13	$0.52	$0	41K
LiteLLMqwen3-30b-a3b	N/A	$0.15	$0.6	$0.015	N/A
LiteLLMaccounts/fireworks/models/qwen3-30b-a3b	N/A	$0.15	$0.6	$0.015	N/A
LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-30b-a3b	N/A	$0.15	$0.6	$0.015	N/A

Capabilities

Reasoning
Tool calling
Structured output
Open weights
In: text
In: image
Out: text

Knowledge cutoff: 2025-04Released: 2025-04-29Family: qwen

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

Download for macOS

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.