What is Qwen3-Coder-480B-A35B good for?

Repository-scale agentic coding, browser use and tool calling, at the heavy end of the open Qwen3-Coder checkpoints. Apache 2.0 weights, on a multi-GPU node.

When is Qwen3-Coder-480B-A35B not a good fit?

Self-hosting on ordinary hardware: memory follows the full 480B parameters, not the 35B active. It is non-thinking only, takes no image or video input, and has 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-480B-A35B?

Hosted, unless you push serious volume. Alibaba Cloud charges $1.50 in / $7.50 out per 1M tokens. The cheapest rental that fits is 8x RTX A6000 at $3,168 a month, which costs the same as about 1B tokens a month on that API.

Can I self-host Qwen3-Coder-480B-A35B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 274 GB of GPU memory, which starts at roughly $3,168 a month on the cheapest rental that fits.

Open weights · Apache 2.0

Qwen3-Coder-480B-A35B

The largest open agentic code model in the Qwen3-Coder family, a 480B MoE with 35B active across 160 experts, built for repository-scale coding workflows.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from Alibaba Cloud

Visit website Compare vs other LLMs →

List price via Alibaba Cloud

Input: $1.50 /1M tokens
Output: $7.50 /1M tokens

Cheapest: $0.38 / $1.55 per 1M tokens via Novita

2 providers

Key Specifications

Context window: 262K tokens
Max output: 66K tokens
Parameters: 480B, 35B active
Inputs: Text

Capabilities Show details: Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input /1M tokens	Output /1M tokens	Cost at 10M in + 2M out
Novita Cheapest	$0.38	$1.55	$6.90	View
Alibaba Cloud Creator	$1.50	$7.50	$30.00	View

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-480B-A35B needs about 274 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX A6000 at about $3,168 a month.

That costs the same as roughly 1B tokens a month on Alibaba Cloud's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo	Break-even vs API
4-bitINT4 / FP4	274 GB333 GB	8× RTX A6000	$3,168$3,168	1B tokens /mo1B tokens /mo
8-bitFP8 / INT8	490 GB549 GB	8× A100	$10,138$10,138	4B tokens /mo4B tokens /mo
16-bitFP16 / BF16	970 GB1,029 GB	4× B300	$22,723$22,723	9B tokens /mo9B tokens /mo

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. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Qwen3-Coder-480B-A35B by blended rate, each at its own cheapest provider.

Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Qwen3-Coder-480B-A35B
DeepSeek V4 Pro DeepSeek	$0.5233	$0.45	$0.89	1M		−9%
GPT-5 Mini OpenAI	$0.5417	$0.25	$2.00	400K	May 2024	−6%
DeepSeek V3 Turbo DeepSeek	$0.55	$0.40	$1.30	64K		−4%
Qwen3-VL-30B-A3B Thinking Alibaba Cloud	$0.5667	$0.20	$2.40	262K		−1%
Qwen3-235B-A22B Thinking (2507) Alibaba Cloud	$0.575	$0.23	$2.30	262K		0%
Qwen3-Coder-480B-A35B This model Alibaba Cloud	$0.575	$0.38	$1.55	262K
GPT-4.1 Mini OpenAI	$0.60	$0.40	$1.60	1M	Jun 2024	+4%
Gemini 2.5 Flash Google Cloud	$0.6667	$0.30	$2.50	1M	Jan 2025	+16%
Gemini 3.5 Flash-Lite Google Cloud	$0.6667	$0.30	$2.50	1M	Mar 2026	+16%
GPT-3.5 Turbo OpenAI	$0.6667	$0.50	$1.50	16K	Sep 2021	+16%
Mistral Large 3 Mistral	$0.6667	$0.50	$1.50	256K		+16%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

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

Frequently Asked Questions

What is Qwen3-Coder-480B-A35B good for?: Repository-scale agentic coding, browser use and tool calling, at the heavy end of the open Qwen3-Coder checkpoints. Apache 2.0 weights, on a multi-GPU node.
When is Qwen3-Coder-480B-A35B not a good fit?: Self-hosting on ordinary hardware: memory follows the full 480B parameters, not the 35B active. It is non-thinking only, takes no image or video input, and has 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-480B-A35B?: Hosted, unless you push serious volume. Alibaba Cloud charges $1.50 in / $7.50 out per 1M tokens. The cheapest rental that fits is 8x RTX A6000 at $3,168 a month, which costs the same as about 1B tokens a month on that API.
Can I self-host Qwen3-Coder-480B-A35B?: Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 274 GB of GPU memory, which starts at roughly $3,168 a month on the cheapest rental that fits.

More from Alibaba Cloud

Model	Context	Input /1M	Output /1M
Qwen3-235B-A22B Thinking (2507) Open weights	262K	$0.23	$2.30
Qwen3-VL-30B-A3B Thinking Open weights	262K	$0.20	$2.40
Qwen3-VL-235B-A22B Instruct Open weights	262K	$0.30	$1.50
Qwen3.6-Flash	1M	$0.25	$1.50
Qwen3.5-Plus	1M	$0.40	$2.40
Qwen3-VL-Plus	262K	$0.20	$1.60
Qwen3.7-Plus	1M	$0.28	$1.10
Qwen2.5-72B Instruct Open weights	33K	$0.38	$0.40