> ## Documentation Index
> Fetch the complete documentation index at: https://docs.opper.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Roundtable

> Ask several models the same question in parallel, then consolidate or compare their answers.

<Warning>
  Roundtable is in **beta**. Its request and response shapes may change without the usual deprecation window.
</Warning>

`POST /v3/roundtable` sends one prompt to several models in parallel and brings their answers back together. Instead of trusting a single model, you get a panel: ask three models the same question and either merge their responses into one consolidated answer or compare them side by side. It runs on the same gateway, key, routing, and tracing as every other call.

Use it when an answer is high-stakes or subjective and a second (and third) opinion is worth the extra cost: architecture decisions, evals and grading, content review, or any "let's see what a few good models think" moment.

## How it works

1. **Fan out** — your `input` goes to every model in `models`, in parallel.
2. **Resolve** — depending on the resolution mode, the results are consolidated into one answer, returned as-is, or voted into a single choice.
3. **Return** — you get the consolidated `data`, aggregated `meta` (models used, total cost, duration), and the per-model `model_results`.

## Resolution modes

| Mode                | What you get                                                                                                              |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------- |
| `summary` (default) | A consolidation model merges every answer into one `data`. Best when you want a single, reconciled response.              |
| `fast`              | No consolidation — `data` is null and you read `model_results` directly. Best when you want to compare answers yourself.  |
| `multiple_choice`   | Each model picks from the `choices` you supply; the result is the consolidated winner. Best for classification or voting. |

In `summary` mode you can override the consolidation model with `summary_model`. In `multiple_choice` mode, pass the literal options in `choices`.

## Shared options

These apply across every model in the panel:

| Field                        | What it does                                                                                     |
| ---------------------------- | ------------------------------------------------------------------------------------------------ |
| `instructions`               | A system prompt shared by all model calls.                                                       |
| `output_schema`              | A JSON Schema applied to every model and the consolidation, so each answer comes back validated. |
| `stream`                     | Stream progress over SSE — per-model deltas, then the consolidation.                             |
| `max_retries` / `timeout_ms` | Per-model retry count and timeout covering all retries.                                          |

Each entry in `models` can also override `temperature`, `max_tokens`, `top_p`, and `reasoning` effort for that model alone.

## What's next

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/build/roundtable/quickstart">
    Run your first roundtable in a few lines.
  </Card>

  <Card title="API reference" icon="square-terminal" href="/v3-api-reference/roundtable/create-roundtable">
    The full request and response schema.
  </Card>

  <Card title="Models" icon="brain" href="/capabilities/models">
    Pick the models for your panel.
  </Card>

  <Card title="Structured output" icon="braces" href="/build/gateway/structured-output">
    Constrain every answer to a schema.
  </Card>
</CardGroup>