Skip to main content
Qwen2.5-VL-7B-Instruct is a vision model available through Starrise AI via an OpenAI-compatible API.

​
Key Capabilities

  • OpenAI compatible — Drop-in replacement for the OpenAI SDK with no code changes required
  • Long context — Supports large document processing and multi-turn conversations
  • Streaming — Real-time token streaming via SSE
  • Strong reasoning — Ideal for complex multi-step tasks

​
Quick Example

curl https://ai.alad.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-vl-7b-instruct",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ]
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be qwen2.5-vl-7b-instruct
messagesarrayYesArray of {{ role, content }} objects
max_tokensintegerNoMaximum number of tokens to generate
temperaturefloatNo0–2, controls randomness, default 1
streambooleanNoEnable SSE streaming, default false
top_pfloatNoNucleus sampling threshold, default 1
stopstring / arrayNoSequences that trigger generation stop

API Reference

View the interactive API Playground for Qwen2.5-VL-7B-Instruct.