Qwen2.5 72B Instruct

Name: Qwen2.5 72B Instruct
Author: OpenRouter

apache-2.072B

Qwen2.5 72B is the latest series of Qwen large language models.

Context

33K

Max output

16K

Input price

$0.36/1M tokens

Output price

$0.4/1M tokens

Capabilities

Show unsupported (1)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Batch Processing

Fine-tuning

Details

Model IDqwen/qwen-2.5-72b-instruct

ProviderOpenRouter

CreatorQwen

Familyqwen

Licenseapache-2.0

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters72B

Architecture—

Context window33K tokens

Max input—

Max output16K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2024-09-19

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.36

Output

$0.4

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: qwen

Model	Caps	Perf	Speed	Context	Max out	Pricing
Qwen: Qwen-Turbo	RTJJMSB	—	—	131K	8K	$0.03$0.13
Qwen: Qwen2.5 7B Instruct	RTJJMSBF	—	—	33K	29K	$0.1$0.2
Qwen: Qwen VL Plus	JJM	—	—	131K	8K	$0.14$0.41
Qwen: Qwen2.5-VL 7B Instruct	RTJJMSBF	—	—	33K	—	$0.2$0.2
Qwen: Qwen Plus 0728 (thinking)	RTJJM	—	—	1M	33K	$0.26$0.78
Qwen: Qwen-Plus	RTJJMSB	—	—	1M	33K	$0.26$0.78
Qwen2.5 72B Instruct	RTJJMSBF	—	—	33K	16K	$0.36$0.4
Qwen: Qwen VL Max	TJJM	—	—	131K	33K	$0.52$2.08
Qwen2.5 Coder 32B Instruct	JJMS	—	—	33K	29K	$0.66$1
Qwen: Qwen-Max	RTJJMSB	—	—	33K	8K	$1.04$4.16

API

GET/v1/models/openrouter/qwen/qwen-2.5-72b-instruct