Alibaba QwenactiveOpen Source

Qwen2.5-72B Instruct

qwen2.5-72b-instruct

Previous-gen flagship. 72B dense model with strong all-around performance.

Context Window

131.1K

tokens

Max Output

8.2K

tokens

Input Price

$0.90

per 1M tokens

Output Price

$3.60

per 1M tokens

Details

Familyqwen2.5

Parameters72B

Training Cutoff2024-06-01

ReleasedSeptember 19, 2024

Capabilities

VisionFunctionsStreamingJSON ModeCodeTool UseMultimodal

Documentation

https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions

Evaluation Scores(4 benchmarks)

HumanEvalFunction-level Python code generation

80.4%

MATH-500Competition-style math

76.2%

MMLU-ProHarder successor to MMLU

71.1%

GPQA DiamondPhD-level science questions

49%

Quick Access

curl pikaainews.com/api/models/qwen-qwen2-5-72b-instruct

npx pika-models info qwen-qwen2-5-72b-instruct

Get API Access

Official

DashScope (Alibaba)

Official Qwen API via Alibaba Cloud.

Third-Party Providers & Aggregators

Cerebras

Wafer-scale inference. 1000+ tokens/sec for select models.

DeepInfra

Lowest per-token rates for open-source models.

Fireworks AI

Fastest inference engine. Multimodal support, HIPAA/SOC2.

Groq

Ultra-fast LPU inference. Best latency for real-time apps.

OpenRouter

500+ models, one API key. Pay-per-token, no minimums.

SiliconFlow

China-optimized inference. Strong Qwen/DeepSeek support.

Together AI

Fast open-source model inference. Sub-100ms latency.

Other qwen2.5 models

Qwen

Qwen2.5-7B Instruct

qwen2.5-7b-instruct

131.1K ctx$0.10/1M

Qwen

Qwen2.5-14B Instruct

qwen2.5-14b-instruct

131.1K ctx$0.40/1M