Home
/
Models
/
QVQ-72B-Preview

QVQ-72B-Preview API

QVQ-72B-Preview enhances visual reasoning with multimodal capabilities for advanced problem-solving across various domains.
Output
Try now
View Docs

How to use QVQ-72B-Preview API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to .

OpenAI-compatible — swap the base URL and it works with your existing SDK.

QVQ-72B-Preview API Pricing

TypePrice
Input
Output

QVQ-72B-Preview vs other models

ModelInputOutputContextBest for
QVQ-72B-Preview
This page
GPT-5.5
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
Claude Sonnet 5
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
Kimi K3
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
Gemini 3.5 Flash
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Yes, QVQ-72B-Preview can stream responses as they are generated.

Yes, QVQ-72B-Preview supports both function calling and structured outputs.

QVQ-72B-Preview was built by Alibaba Cloud.

Related chat models

Kimi K3
Moonshot AI
Input
$3.9 / 1M tokens
Output
$19.5 / 1M tokens
View model →
DeepSeek V4 Pro
DeepSeek
Input
$0.5655 / 1M tokens
Output
$1.131 / 1M tokens
View model →
MiniMax M3
MiniMax
Input
$0.39 / 1M tokens
Output
$1.56 / 1M tokens
View model →
Gemini 3.5 Flash
Google
Input
$0.65 / 1M tokens
Output
$3.9 / 1M tokens
View model →

Related blog posts

Best AI Models for Agentic Workflows and Tool Use in 2026

Agentic workflows are AI systems that plan, act, and use tools autonomously. Pick the wrong model, and automations fail while compute is wasted.

Read article →

Best LLMs for Long-Context & Multimodal Tasks in 2026

The unified AI API that puts every frontier model one call away. This guide cuts through the noise so you pick the right model for the job, not the most hyped one.

Read article →

Start building with QVQ-72B-Preview

Get API Key
1000+ models, one API.