Fusion
openrouter:fusion
Lets a model convene a panel of other models and an analyst mid-request. The panel answers independently, the analyst surfaces consensus, contradictions, coverage gaps, unique insights, and blind spots, and the calling model uses the report to answer.
How it works
For research, critique, and compare-and-contrast prompts, or anything where being wrong is expensive. Simple prompts will not trigger it.
Your model calls Fusion when a task benefits from several perspectives.
A panel of models answers in parallel, three by default, with web search and fetch.
An analyst model compares the answers for consensus, contradictions, gaps, and unique insights.
Your model writes the final answer from the analysis.
Providers and pricing
OpenRouter
Model token usage
Billed as normal token usage on each model the panel and analyst run.
Standard model token costs apply to every request.
Using this tool
OpenRouter runs the tool during the request and returns the result to the model, so no client-side tool loop is needed.
Supported APIs: Chat Completions and Responses.
curl https://openrouter.ai/api/v1/responses \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.2",
"tools": [
{
"type": "openrouter:fusion"
}
],
"input": "Should a small team adopt a monorepo? Consult a panel before answering."
}'Setup, parameters, and examples in the docs.
Read the integration guide