whichllm — Browse and compare AI model specs and pricing

Charm Hyper

Qwen3-Coder 480B-A35B Instruct model ID, context window & pricing

qwen

Quick facts

Model ID qwen3-coder-480b-a35b-instruct-int4-mixed-ar
Source Charm Hyper
Context Window 106000
Pricing $0.57 input / $2.13 output per 1M tokens
Capabilities tool calling, temperature control, open weights

Model overview

Qwen3-Coder 480B-A35B Instruct is an AI model from Charm Hyper with 106000 token context window and text input support.

Published pricing is $0.57 input and $2.13 output per 1M tokens.

  • Workloads that use text inputs with text outputs.
  • Agent and tool workflows that need function calling.
Model ID qwen3-coder-480b-a35b-instruct-int4-mixed-ar
Provider Charm Hyper
Family qwen
Status -
Knowledge Cutoff 2025-04
Release Date 2026-04-30
Input Modalities text
Output Modalities text
Context Window 106000
Input Limit -
Output Limit 10600
Tool Calling Yes
Reasoning No
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.57
Output Cost / 1M tokens $2.13
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens $0.28