Fusion

Fusion is a server tool: BitRouter runs it mid-generation instead of handing the call back to your client. A panel of models answers your prompt in parallel, a judge model compares (not merges) their answers into structured analysis, and the calling model writes the final answer grounded in that analysis. Use it for hard, high-stakes questions where one model's blind spots are worth catching.

Quick start

The simplest way to use Fusion is the bitrouter/fusion model alias — set it as your model and BitRouter expands it into a deliberation using your deployment's default panel and judge. This works on any protocol, including Chat Completions:

<Tabs items={['Model alias (cURL)', 'Explicit panel (Responses)']}>

curl https://api.bitrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $BITROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bitrouter/fusion",
    "messages": [
      {"role": "user", "content": "Should we migrate our event pipeline from Kafka to a managed alternative? Trade-offs."}
    ]
  }'

The alias rewrites the request onto a default outer model, attaches the Fusion declaration, and nudges the model to call the tool once. You get back a single, deliberated answer.

Declare Fusion yourself to pick the exact panel, judge, and (optionally) a dedicated synthesizer. Fusion rides the request tools array as a server tool:

curl https://api.bitrouter.ai/v1/responses \
  -H "Authorization: Bearer $BITROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.8",
    "input": "Should we migrate our event pipeline from Kafka to a managed alternative?",
    "tools": [
      {
        "type": "fusion",
        "panel": [
          {"model": "anthropic/claude-opus-4.8"},
          {"model": "openai/gpt-5.5"},
          {"model": "google/gemini-3-pro-preview"}
        ],
        "judge": {"model": "anthropic/claude-opus-4.8"}
      }
    ]
  }'

How it works

1. Panel — every model in the panel answers your prompt in parallel. Each member can be given provider web tools (e.g. web search) to ground its answer.
2. Judge — the judge model compares the panel's answers and returns structured analysis: consensus, contradictions, partial_coverage, unique_insights, and blind_spots. The judge compares, it does not merge — it surfaces where the models agree and disagree rather than blending them into mush.
3. Synthesis — the calling model (or a dedicated synthesizer) reads that analysis and writes the final answer.

Configuration

Declared on the tools-array entry:

The deployment-wide defaults that the bitrouter/fusion alias expands to — panel, judge, synthesizer, and the web tools forwarded to every member — are set in the server_tools.fusion config section. An explicit declaration on a request overrides them.

On Cloud

Fusion is enabled and managed on BitRouter Cloud — a curated default panel and judge back the bitrouter/fusion alias out of the box, with per-run cost and the full panel→judge→synthesis chain visible in the request log. Self-hosters enable it by adding a server_tools.fusion block to their config (its presence turns on both the fusion server tool and the bitrouter/fusion alias).

See also

• Sub-agent — delegate a self-contained task to a single worker model
• Advisor — consult one stronger model mid-task
• Provider selection — control which provider serves each panel model