Alibaba QwenactiveOpen Source

QVQ-72B

qvq-72b-preview

Visual reasoning model. Thinks step-by-step about images and videos.

Context Window

131.1K

tokens

Max Output

8.2K

tokens

Input Price

$1.50

per 1M tokens

Output Price

$6.00

per 1M tokens

Details

Familyqvq

Parameters72B

Training Cutoff2024-10-01

ReleasedDecember 24, 2024

VisionStreamingReasoningMultimodal

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

curl pikaainews.com/api/models/qwen-qvq-72b

npx pika-models info qwen-qvq-72b

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.