Merge Launches Fusion API: Parallel Multi-Model Panel with Judge Claims to Beat Frontier Models
shensi · x · 2026-07-31
Merge has launched its new Fusion API, aiming to deliver better-than-frontier-model performance at a fraction of the cost.
The core mechanism sends a prompt in parallel to a panel of models. After they answer independently, a 'judge model' synthesizes their responses along with its own analysis to produce a single final output.
The company states that model disagreement and differing reasoning paths serve as useful signals. Using this multi-agent collaboration architecture, Fusion reportedly beats standalone performance of Fable-level models at about a quarter of the cost. Following this launch, Merge experienced its best signup week yet.
Related event: Merge Launches Fusion API with Multi-Model Parallelism and Judge Mechanism(2 posts)→
More from coding & agent
- Open-source UML lets Claude and ChatGPT share memory via a visual knowledge graph — Far_Pangolin_7657 · 2026-07-31
- Comparing 4 AI Agent Observability Platforms: Logfire Takes the Crown with Native SQL — samuelcolvin · 2026-07-31
- Testing Opus 5: Building a ThreeJS App Zooming Across Nine Powers of Ten — omarsar0 · 2026-07-31
- Developer Shares Codex Micro Workflow: Monitor AI Agents Between Workout Sets — rudrank · 2026-07-31
- Open-Source Autonomous OS Deployed on Reachy Mini Robot Hardware — dee_hw · 2026-07-31
- Rails Solid Queue 1.6 Released: Optimized for Long-Lived LLM Jobs — kieranklaassen · 2026-07-31