SiliconFlow (China)

Qwen/Qwen2.5-72B-Instruct

Name: Qwen/Qwen2.5-72B-Instruct
Brand: SiliconFlow (China)

Canonical ID: siliconflow_cn/Qwen/Qwen2.5-72B-Instruct

More SiliconFlow (China) models More qwen2.5-72b-instruct family models

Qwen/Qwen2.5-72B-Instruct is listed under SiliconFlow (China) in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.

Reasoning: No Tool use: Yes

Overview

text

Provider: SiliconFlow (China)
Family: qwen2.5-72b-instruct
Release date: 2024-09-18
Last updated: 2025-11-25
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.59/1M
Output: $0.59/1M
Cached input: N/A

Context and output

Context window: 33,000
Max output tokens: 4,000
Qualified ID: siliconflow_cn/Qwen/Qwen2.5-72B-Instruct

Model Summary

Qwen/Qwen2.5-72B-Instruct is a model listing in the SiliconFlow (China) provider catalog. It is categorized under the qwen2.5-72b-instruct family.

The model supports text modalities across input/output paths. Reported context capacity is 33,000. Pricing is listed at $0.59/1M input and $0.59/1M output.

Same Family: qwen2.5-72b-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Qwen 2.5 72B Instruct abacus/Qwen/Qwen2.5-72B-Instruct	Abacus	128,000	$0.11/1M	$0.38/1M	Tools
Qwen2.5 72B Instruct chutes/Qwen/Qwen2.5-72B-Instruct	Chutes	32,768	$0.13/1M	$0.52/1M	Tools
Qwen/Qwen2.5-72B-Instruct siliconflow/Qwen/Qwen2.5-72B-Instruct	SiliconFlow	33,000	$0.59/1M	$0.59/1M	Tools

Qwen/Qwen2.5-72B-Instruct

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From SiliconFlow (China)

ascend-tribe/pangu-pro-moe

baidu/ERNIE-4.5-300B-A47B

ByteDance-Seed/Seed-OSS-36B-Instruct

deepseek-ai/DeepSeek-OCR

deepseek-ai/DeepSeek-R1

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

deepseek-ai/DeepSeek-V3

Same Family: qwen2.5-72b-instruct