LLM Reference

Using Qwen2.5-72B-Instruct on SiliconFlow

Implementation guide · Qwen2.5 · Alibaba

Serverless

Quick Start

  1. 1
    Create an account at SiliconFlow and generate an API key.
  2. 2
    Use the SiliconFlow SDK or REST API to call qwen2.5-72b-instruct.
  3. 3
    You'll be billed $0.28/1M input, $0.28/1M output tokens.
API Portal

Code Examples

Code examples for this provider have not been sourced yet.

About SiliconFlow

SiliconFlow is a model serving platform for open and closed model inference, offering fast and cost-effective API access to popular AI models.

View all models on SiliconFlow →

Pricing on SiliconFlow

TypePrice (per 1M)
Input tokens$0.28
Output tokens$0.28

Capabilities

Structured Outputs

About Qwen2.5-72B-Instruct

Instruction-optimized flagship variant for demanding production applications requiring high-accuracy complex problem-solving across industries.

Full model details →

Model Specs

Released2024-06-07
Parameters72.7B
Context128K
ArchitectureDecoder Only

More Models on SiliconFlow

Qwen2.5-32B-InstructQwen2.5-14B-InstructQwen2.5-7B-Instruct
All models on SiliconFlow →

Also available on(6)

Chutes AI$0.18/1MDeepInfra$0.36/1MOpenRouter$0.36/1M
Compare all providers →

Provider

SiliconFlow