Back to all models

Qwen2.5 72B Instruct

Qwen 2.5 instruction model, 72B size.

qwen25-72b-instruct

STABLEModel DeactivatedGet Started

32,768 context

Starting at $0.13/M input tokens

Starting at $0.40/M output tokens

Streaming

Tools

JSON Output

Select Provider

All Providers for Qwen2.5 72B Instruct

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

Nebius AI

Context: 32.8k

Deactivated since Nov 3, 2025

Input

$0.13

/M tokens

Cached

—

/M tokens

Output

$0.4

/M tokens