qwen/qwen-2.5-72b-instruct

Qwen/Qwen-2.5-72B-Instruct

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

Qwen-2.5-72B-Instruct is Alibaba's flagship 72B parameter model featuring enhanced reasoning, 128K context, and advanced tool-calling capabilities. Excels in multilingual tasks, technical domains, and complex instruction following with improved safety alignment.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita

Available

Input tokens

$0.380 / 1M tokens

Output tokens

$0.400 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.380 / 1M tokens
Output tokens	$0.400 / 1M tokens

Performance

Published evaluation results associated with this model.

General Reasoning

MMLU81.9

ARC-Challenge88.7

HellaSwag87.3

Winogrande83.9

Mathematical Reasoning

GSM8K93.7

MATH52.8

Coding

HumanEval74.6

MBPP77.8

CRUXEval70.3

Multilingual

XTREME84.2

Flores-10176.8

MGSM85.4

CMMLU80.1

Long-Context

Needle-128K98.9

PG-22 Recall94.3

MultiDocQA90.7

Safety & Alignment

ToxiGen94.5

TruthfulQA71.8

Harmfulness0.9

Efficiency

Tokens/sec (8×A100)52

First Token Latency0.92

VRAM Utilization148

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen-2.5-72B-Instruct",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'