# Synero API

> Collective AI Intelligence — query 4 AI models simultaneously and get a synthesized answer.

Synero sends your prompt to a council of 4 AI advisors (each powered by a different leading model), then a synthesizer produces a single unified answer that combines the best of all perspectives.

## API Endpoint

POST https://synero.ai/api/query

## Authentication

Use a Bearer token in the Authorization header:

    Authorization: Bearer sk_live_your_key_here

Get your API key at: https://synero.ai/app/api-keys

## Quick Start

    curl -X POST https://synero.ai/api/query \
      -H "Authorization: Bearer sk_live_your_key_here" \
      -H "Content-Type: application/json" \
      -d '{"prompt": "What are the trade-offs between microservices and monoliths?"}'

The response is a server-sent events (SSE) stream.

## Request Body (JSON)

- prompt (string, required): The question to ask the council. Max 10,000 characters.
- config (object, optional): Customize which model powers each advisor.
  - advisorModels (object): Map of slot ID to model ID.
    - architect: ModelId (default: "gpt-4.1")
    - philosopher: ModelId (default: "claude-sonnet-4-6")
    - explorer: ModelId (default: "gemini-3-flash-preview")
    - maverick: ModelId (default: "grok-4-1-fast-reasoning")
  - synthesizerModel: ModelId (default: "claude-sonnet-4-6")
- threadId (string, optional): UUID for multi-turn conversation threads.
- parentQueryId (string, optional): ID of the previous query in a thread.
- threadHistory (array, optional): Previous prompt/synthesis pairs for context.

## SSE Response Events

The response streams these event types:

| Event | Data Fields | Description |
|-------|-------------|-------------|
| advisor | id, token, status | Incremental token from an advisor |
| advisor-complete | id, modelId, inputTokens, outputTokens, latencyMs | Advisor finished responding |
| advisor-error | id, error | Advisor encountered an error |
| synthesis | token, status | Incremental token from the synthesizer |
| synthesis-complete | inputTokens, outputTokens | Synthesis finished |
| complete | queryId | Entire council query is done |
| error | message | Fatal error occurred |

Advisor slot IDs: architect, philosopher, explorer, maverick.

## Available Models

### OpenAI
- gpt-5.4
- gpt-5.2
- gpt-4.1
- gpt-4.1-mini
- o4-mini

### Anthropic
- claude-opus-4-6
- claude-sonnet-4-6
- claude-haiku-4-5

### Google
- gemini-3.1-pro-preview
- gemini-3-flash-preview
- gemini-2.5-pro
- gemini-2.5-flash

### xAI
- grok-4
- grok-4-1-fast-reasoning
- grok-3-mini

## Default Council Configuration

    {
      "advisorModels": {
        "architect": "gpt-4.1",
        "philosopher": "claude-sonnet-4-6",
        "explorer": "gemini-3-flash-preview",
        "maverick": "grok-4-1-fast-reasoning"
      },
      "synthesizerModel": "claude-sonnet-4-6"
    }

## Advisor Personas

- Architect: Structured, analytical, methodical thinker
- Philosopher: Nuanced, thorough, precise reasoning
- Explorer: Creative, curious, makes cross-domain connections
- Maverick: Bold, unconventional, contrarian perspective

## Rate Limits

- 60 requests per minute per API key
- Rate limit headers included in responses: X-RateLimit-Limit, X-RateLimit-Remaining, Retry-After

## Error Codes

- 400: Bad request (missing prompt, invalid config)
- 401: Invalid API key
- 402: Payment required (no subscription or insufficient credits)
- 429: Rate limit exceeded
- 503: Billing service temporarily unavailable

## Links

- OpenAPI Spec: https://synero.ai/openapi.json
- API Key Dashboard: https://synero.ai/app/api-keys
- Developer Docs: https://synero.ai/developers
- Main Site: https://synero.ai