Providing developers the best model for the task at hand has always been our goal. Earlier this year, we made that easier by launching Auto model selection, which reviews your task and matches it to the best-suited model for that task. Today, we’re introducing Project Hydra Fusion, a research preview that delivers frontier intelligence through runtime orchestration. It creates a full execution plan, choosing from models across multiple providers to draft, critique and revise, or cascade to more powerful models to complete your task.

Hydra Fusion fills a key role in our overall strategy to deliver automated semantic routing between local, cloud, and compound models. For developers, that complexity stays behind the scenes: you select Hydra Fusion like any other model, and it chooses a workflow that balances performance, cost, and latency for each task. Hydra Fusion treats workflow selection as an optimization problem. It uses capability signals for reasoning, code generation, debugging, and tool use to select the most efficient execution pattern to meet the quality bar.

For each request, Hydra Fusion currently chooses one of three execution patterns: Single, Cascade, or Critique. Each pattern addresses a different quality-to-cost trade-off. In offline evaluations across three agentic coding benchmarks, Hydra Fusion consistently demonstrated frontier-level quality with substantial estimated cost savings. On Terminal Bench 2.1, it improved verified task quality by 4.9 percentage points at 67% lower estimated cost compared with Claude Opus 5.