Product — Council Verification

Five models.
One answer.

Single-model answers hallucinate confidently. Five models from different providers rarely agree on the same wrong answer. When accuracy matters, run a council and let the disagreement surface before your agent acts on a bad output.

Council Verification

Multi-model verification on demand.

One model can hallucinate. Five rarely agree on the same wrong answer. Add mode: "council" to any request when accuracy matters more than latency. Pricing scales 5x to cover the parallel inference — honest, no hidden cost.

01

3–7 models answer in parallel

Diverse providers picked by topic and complexity. Avoids single-vendor bias and single-model failure modes.

02

Agreement scored

Embedding cosine similarity on paid tier, Jaccard word-overlap on free. Each answer gets an agreement score against the others.

03

Chairman synthesizes on disagreement

Confidence below 0.6? A separate Chairman model reads all answers and the critiques and synthesizes the final response.

Recommended for legal, medical, financial, and audit-grade prompts. For everyday traffic, default smart routing already picks the best single model — no need to pay 5x.

Request shape

Same API. One extra field.

POST /v1/chat/completions
{
  "messages": [...],
  "mode": "council",        // 3-7 models in parallel
  "budget": "auto"          // tier picks model class
}

// Response (200 OK)
{
  "choices": [{ "message": { "content": "..." } }],
  "council": {
    "models_queried": 5,
    "consensus_confidence": 0.92,
    "agreement_pct": 88,
    "chairman_used": false,
    "votes": [
      { "model": "google/gemini-2.5-pro", "matches_consensus": true  },
      { "model": "anthropic/claude-sonnet-4-5", "matches_consensus": true  },
      { "model": "openai/gpt-5.1", "matches_consensus": true  },
      { "model": "deepseek/deepseek-chat", "matches_consensus": true  },
      { "model": "z-ai/glm-5", "matches_consensus": false }
    ]
  }
}
When to use

Legal, medical, financial, audit. Anything where one hallucinated answer creates more damage than five right ones cost.

When not to

Latency-sensitive chat. Casual Q&A. Anything where a single smart-routed model already gets you 95% of the way.