Fusion
Multi-model panel — Fable 5 + GPT-5.5, ensembled. Beats Fable 5 at half the price.
Reference benchmarks for Fusion
These are external benchmarks I pulled from the source comparison guides on agentos.guide — SWE-bench Verified, DRACO, Kilo plan rubric, build-time measurements, vendor-reported coding scores. They are not goldiebench medal scores (those come only from same-prompt one-shot creative coding tasks in the matrix). I surface them here so the spec sheet for Fusion is honest about what's measured.
What is Fusion?
Fusion is the OpenRouter frontier model with a Varies — depends on which panel models are dispatched context window, released 2026-06-14. Tagline: Multi-model panel — Fable 5 + GPT-5.5, ensembled. Beats Fable 5 at half the price.. Official source: openrouter.ai/openrouter/fusion.
Pricing detail. OpenRouter's Fusion API dispatches a single prompt to multiple frontier models and ensembles the answers. Premium panel: Fable 5 + GPT-5.5. Budget panel: cheaper open-weights models. Roughly half the per-token cost of a Fable 5 solo call.
How I use it inside the Agent OS. Dispatched from Agent OS for research-heavy prompts where ensemble accuracy outweighs single-model speed.
What I built with Fusion
Every model on Goldie Bench gets the same fixed prompt set — one shot, single HTML file out — and I score the result 0–10 inside the Agent Operating System. Here's what Fusion shipped on the bench: 47 one-shot demos across Varies — depends on which panel models are dispatched of context. Of those, 47 are scored against the field with my honest 0–10 from the source guides at agentos.guide.
Strengths
- Premium Fusion panel scored 69.0% on DRACO deep-research benchmark — beats solo Fable 5 by +3.7 points
- Budget panel ties Fable 5 at ~64.7% for roughly half the cost
- Vendor-agnostic — model panel can swap as new frontier releases land
Trade-offs
- Ensemble latency higher than any single model (panel calls run in parallel but the slowest still gates the response)
- No per-task goldiebench scoring yet — bench rank pending
Best for
- Deep-research workflows where panel consensus beats single-model answers
- Cost-sensitive operators who want Fable-5-class output at ~half the bill
- Production agents that benefit from vendor-redundancy on every call
Every benchmark — Fusion's full scorecard
All 47 scored tasks, best first — the judge's 0–10 on the same rubric as the whole field. Click any bar for that task's cross-model page, or open this scorecard in the interactive graphs. Full editorial breakdown with judge quotes and sourced outside research: the Fusion deep dive →.
Every demo by Fusion
47 live demos, sorted by category. Click any tile to play the actual one-shot result. Verdicts and 0–10 scores are pulled from the source guides where I posted them publicly.
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVECompare Fusion against every other model
Every head-to-head featuring Fusion. Verdicts shown for scored pairs.
See all 66 comparisons across every model →
Quick pill index
Direct comparisons against every other scored model on the bench:
Fusion vs Claude Opus 5 Fusion vs Hermes MoA Fusion vs GPT-5.6 Sol Fusion vs Claude Fable 5 Fusion vs Qwen 3.8 Fusion vs Grok Fusion vs MiniMax M3 Fusion vs Fugu Ultra Fusion vs Kimi K3 Fusion vs GLM-5.2 Fusion vs Fugu Mini Fusion vs Opus 4.8 Fusion vs Kimi K2.7 Fusion vs Qwable 5 27B Coder Fusion vs Gemini 3.6 Flash Fusion vs Claude Sonnet 5 Fusion vs Qwen 3.7 Fusion vs Fugu Ultra 1.1 Fusion vs Inkling Fusion vs Agents-A1 Fusion vs Gemma 4 12B · MLX Fusion vs Laguna XS 2.1 Fusion vs Qwythos 9B Fusion vs LongCat-2.0 Fusion vs Hy3 Fusion vs Gemma-4 12B CoderRead more on agentos.guide: /fusion-api
Fusion — frequently asked
What is Fusion?
Fusion is OpenRouter's AI model — Multi-model panel — Fable 5 + GPT-5.5, ensembled. Beats Fable 5 at half the price. It has a Varies (per-panel) context window and was released 2026-06-14.
How good is Fusion at coding and one-shot builds?
On the GoldieBench one-shot build benchmark it averages 8.59/10 across 47 scored tasks, with 21 gold, 3 silver and 3 bronze medals.
How much does Fusion cost?
OpenRouter Fusion API pricing. OpenRouter's Fusion API dispatches a single prompt to multiple frontier models and ensembles the answers. Premium panel: Fable 5 + GPT-5.5. Budget panel: cheaper open-weights models. Roughly half the per-token cost of a
Where can I see Fusion demos?
Every one-shot build is live and playable on this page and on the GoldieBench compare matrix — same prompt as every other model, no retries.
Run this stack yourself.
Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.