Qwen3-Coder-30B-A3B

Code-specialized 30.5B MoE with 3.3B active across 128 experts, small enough to run on consumer hardware for code generation and agentic coding.

Params: 30.5B, 3.3B active
Context: 262K tokens
Max output: 66K
License: Apache 2.0

Visit Alibaba Cloud Compare vs other LLMs →

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Qwen3-Coder-30B-A3B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Qwen3-Coder-30B-A3B, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Alibaba Cloud Creator	Open weights, no hosted price			Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Qwen3-Coder-30B-A3B needs about 20 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 2× RTX 5060 Ti at about $202 a month.

Single node ≤ 8

What it costs to self-host Qwen3-Coder-30B-A3B at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo
4-bit INT4 / FP4	20 GB32 GB	2× RTX 5060 Ti	$202$403
8-bit FP8 / INT8	36 GB45 GB	2× RTX 3090	$360$403
16-bit FP16 / BF16	66 GB89 GB	4× RTX 3090	$720$806

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What Qwen3-Coder-30B-A3B accepts and can do, as published by Alibaba Cloud.

Text Accepts and generates natural-language text.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.

Common questions

What is Qwen3-Coder-30B-A3B good for?

Agentic coding and browser-use tool calling on local hardware. Apache 2.0 weights, a 30.5B mixture of experts with 3.3B active, on a single consumer GPU.

When is Qwen3-Coder-30B-A3B not a good fit?

Tasks that need a reasoning trace, since it is non-thinking only, and general assistant work, where the lineup's non-Coder models fit. No image or video input, and no built-in web search, though a host or your own tool loop can add one.

What is the cheapest way to run Qwen3-Coder-30B-A3B?

No provider we track hosts it; self-hosting on the cheapest rental that fits (2x RTX 5060 Ti, $0.28 per hour) costs about $202 a month.

Can I self-host Qwen3-Coder-30B-A3B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 20 GB of GPU memory, which starts at roughly $202 a month on the cheapest rental that fits.