LLMWise — AI-Readable Overview

{
  "model": "auto",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true
}

{
  "models": [
    "gpt-5.2",
    "claude-sonnet-4.5",
    "gemini-3-flash"
  ],
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing"
    }
  ],
  "stream": true
}

{
  "models": [
    "gpt-5.2",
    "claude-sonnet-4.5",
    "gemini-3-flash"
  ],
  "synthesizer": "claude-sonnet-4.5",
  "strategy": "consensus",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about AI"
    }
  ]
}

{
  "contestants": [
    "gpt-5.2",
    "claude-sonnet-4.5"
  ],
  "judge": "gemini-3-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain recursion"
    }
  ]
}

{
  "model": "gpt-5.2",
  "routing": {
    "strategy": "rate-limit",
    "fallback": [
      "claude-sonnet-4.5",
      "gemini-3-flash"
    ]
  },
  "stream": true
}

model: string (required) — model ID or 'auto'
messages: array (required) — [{role, content}]. Roles: system, user, assistant
stream: boolean (default: true) — enable SSE streaming
temperature: number (0-2, default: 0.7)
max_tokens: number (optional) — max response tokens
cost_saver: boolean (optional) — forces model='auto' and optimization_goal='cost'
optimization_goal: string (optional) — balanced|latency|cost|reliability
semantic_memory: boolean (optional) — semantic recall toggle
semantic_top_k: number (optional) — 1..12
semantic_min_score: number (optional) — 0..1
conversation_id: string (optional) — for conversation threading

model: string (required) — primary model ID
routing: object (required) — {strategy: string, fallback: string[]}
messages: array (required) — [{role, content}]
stream: boolean (default: true)

models: string[] (required, 2-9) — model IDs to compare
messages: array (required) — [{role, content}]
stream: boolean (default: true)
temperature: number (optional)
max_tokens: number (optional)

models: string[] (required, 2-6 for most strategies; exactly 1 for self_moa)
synthesizer: string (required) — model ID for synthesis step
strategy: string (default: 'consensus') — consensus|council|best_of|chain|moa|self_moa
messages: array (required) — [{role, content}]
layers: number (1-3, MoA only) — refinement layers
samples: number (2-8, Self-MoA only, default: 4) — candidate count
temperature: number (optional)

contestants: string[] (required, 2-4) — model IDs to compete
judge: string (required) — model ID for judging (runs at temperature 0.3)
messages: array (required) — [{role, content}]
criteria: string[] (optional) — custom evaluation criteria. Default: accuracy, completeness, clarity, helpfulness, code quality