Skip to main content
DeepSeek V4 Pro is available through Starrise AI via the OpenAI-compatible interface. Supports thinking mode, function calling, and JSON mode.

​
Key Capabilities

  • OpenAI-compatible — Drop-in replacement for the OpenAI SDK, no other code changes needed
  • Thinking mode — Deep thinking with configurable reasoning intensity
  • Function calling — Native support for tools and function calls
  • JSON mode — Structured output via response_format
  • Long context — Supports large document processing and multi-turn conversations
  • Streaming — Real-time token streaming via SSE
  • Prompt caching — Automatic caching with hit/miss statistics returned

​
Quick Example

curl https://ai.alad.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ]
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesFixed value: deepseek-v4-pro
messagesarrayYesArray of { role, content } objects; supports system, user, assistant, tool roles
thinkingobjectNoEnable/disable thinking: {"type": "enabled"} or {"type": "disabled"}. Optional reasoning_effort: high, max, low, medium
max_tokensintegerNoMaximum number of tokens to generate
temperaturefloatNo0–2, controls randomness, default 1
streambooleanNoEnable SSE streaming, default false
stream_optionsobjectNo{"include_usage": true} to return usage statistics at end of stream
top_pfloatNoNucleus sampling threshold, default 1
stopstring / arrayNoSequences where generation stops (up to 16)
response_formatobjectNo{"type": "json_object"} to enable JSON mode
toolsarrayNoList of function calling tools
tool_choicestring / objectNoTool selection control: none, auto, required, or specify a function
user_idstringNoCustom user ID for content safety and KVCache isolation

API Reference

View the interactive API Playground for DeepSeek V4 Pro.