Qwen3 Coder 480B A35B Instruct

Code-specialized Qwen 3 MoE, 480B size.

qwen3-coder-480b-a35b-instruct

262,144 context

Starting at $0.22/M input tokens

Starting at $1.30/M output tokens

Streaming

Tools

JSON Output

Select Provider

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

NovitaAI

Context: 262.1kQuant: fp8

Input

$0.3

/M tokens

Cache Read

—

/M tokens

Output

$1.3

/M tokens

Vertex AI (OpenAI-compatible)

Context: 262.1k

Deactivating on Oct 21, 2026

Input

$0.22

/M tokens

Cache Read

$0.022

/M tokens

Output

$1.8

/M tokens