Qwen3 Coder 480B A35B

qwen/qwen3-coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

InputText
OutputText
Input / Outputclub$1.0335 / $5.1675per 1M tokens · USD
Context window262.1Ktoken
Maximum output65.5Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$1.0335/ 1M token
InputInput length ≥ 32,001 tokensUS$1.8603/ 1M token
InputInput length ≥ 128,001 tokensUS$3.1005/ 1M token
OutputUS$5.1675/ 1M token
OutputInput length ≥ 32,001 tokensUS$9.3015/ 1M token
OutputInput length ≥ 128,001 tokensUS$15.5025/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
262,144 token
Maximum output
65,536 token

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Qwen3 Coder 480B A35B, and who develops it?

Qwen3 Coder 480B A35B is a model from qwen. Its model ID on Vecbase is qwen/qwen3-coder. Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

How much does Qwen3 Coder 480B A35B cost on Vecbase?

For Qwen3 Coder 480B A35B, the Club plan lists USD 1.0335 per 1 million input tokens and USD 5.1675 per 1 million output tokens, as of 10/8/2026, 11:16:05 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Qwen3 Coder 480B A35B’s context window?

Qwen3 Coder 480B A35B has a context window of 262,144 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Qwen3 Coder 480B A35B?

Qwen3 Coder 480B A35B can generate up to 65,536 tokens per response. Your API or request settings may set a lower limit.

Can Qwen3 Coder 480B A35B call tools in an agent workflow?

Yes. Qwen3 Coder 480B A35B supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Qwen3 Coder 480B A35B support structured outputs?

Yes. Qwen3 Coder 480B A35B supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Qwen3 Coder 480B A35B support?

Qwen3 Coder 480B A35B accepts Text and produces Text.

Which providers make Qwen3 Coder 480B A35B available through Vecbase?

Vecbase offers Qwen3 Coder 480B A35B through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Qwen3 Coder 480B A35B?

Use qwen/qwen3-coder as the model identifier for Qwen3 Coder 480B A35B. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access Qwen3 Coder 480B A35B through Vecbase?

To use Qwen3 Coder 480B A35B, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Qwen3 Coder 480B A35B?

We do not yet have a confirmed release date for Qwen3 Coder 480B A35B.

Which models can I compare with Qwen3 Coder 480B A35B on Vecbase?

You can compare Qwen3 Coder 480B A35B with Qwen-Plus (qwen/qwen-plus), Qwen3 235B A22B Instruct 2507 (qwen/qwen3-235b-a22b-2507), and Qwen3 Coder Flash (qwen/qwen3-coder-flash). Check their capabilities and prices to find the best fit for your task.