Qwen2.5 Coder 32b Instruct

Name: Qwen2.5 Coder 32b Instruct
Brand: NVIDIA

Active

Qwen coding model for software agents, repository edits, and code reasoning

Input / 1M tokens

$0.0000

Output / 1M tokens

$0.0000

Record updated 2026-09-03

Modality:LLM

Context:128,000 tokens

Release:Nov 6, 2024

Pricing

Platform

Scope

Input

Output

Details

Official

Standard

$0.0000

128k context · 4k max output

No recent changes.

No benchmark data available.

AI Cost Optimization

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.