Home › Models › Hunyuan Vision 2.0 Instruct
Tencent Hunyuan · Vision 2.0 Instruct · Just Added

Hunyuan Vision 2.0 Instruct API

Tencent's Hunyuan Vision 2.0 Instruct is a fast multimodal vision-language model for image understanding, OCR and visual question answering — at provider list price, zero platform fee.

$1.154
Input / 1M tokens
$2.692
Output / 1M tokens
VLM
Vision + text
$0
Platform fee
Sign Up - Get $2.00 Free Credit See All Pricing

Why use Hunyuan Vision 2.0 Instruct on NovAI?

  • Fast multimodal understanding - instruct-tuned vision-language model for image + text prompts
  • OCR & document reading - extracts text from screenshots, scans, forms and tables
  • Visual question answering - answers detailed questions about image content
  • Chart & scene understanding - interprets visualizations, photos and diagrams
  • Zero platform fee - raw provider list price, no markup
  • OpenAI-compatible - drop-in via /v1/chat/completions with multimodal content

Best use cases

  • Image captioning and description
  • Screenshot and document OCR
  • Visual question answering
  • Chart and infographic parsing
  • Multimodal chat assistants

Quick start

cURL

curl https://aiapi-pro.com/v1/chat/completions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy-vision-2.0-instruct",
    "messages": [{"role":"user","content":"Describe what you see in this image"}]
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.chat.completions.create(
    model="hy-vision-2.0-instruct",
    messages=[{"role":"user","content":"Describe what you see in this image"}],
)
print(resp.choices[0].message.content)

Try Hunyuan Vision 2.0 Instruct today

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up Free