OpenRouter's new Fusion API routes a single prompt through a configurable panel of models that analyze outputs together for consensus, contradictions and gaps before a judge model synthesizes the final answer, targeting deep research work where the company asserts results match Anthropic's latest Fable model at roughly half the cost.
We just announced our Fusion API:
- Fable-level performance on deep research tasks, at half the cost - Better-than-SOTA performance using panels
The future of AI is neurodiversity, not single-model takeovers.
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
The system lets users pick preset panels or define custom ones plus a judge, with optional parallel web search, so the output draws on differing model strengths rather than one monolithic system.
Actual spend equals the sum of every model call plus OpenRouter's fee, with Budget or Quality presets available, yet no third-party benchmarks confirm the Fable comparison or typical real-world pricing.
Many users praised OpenRouter's Fusion API for delivering Fable-level intelligence at half the cost and advancing model orchestration, while others called it lazy, useless, or likely to cause billing problems and bad outputs.
We benchmarked Fusion on 100 hard research tasks and found:
1. Panels of models consistently outperform individual models 2. Beyond-frontier performance can be achieved with frontier panels 3. Panels of budget models can surpass frontier models at a much lower cost
Even more data to support what I have been talking about. The combination of model intelligence (and this includes human expertise) has a compounding effect unlike anything I've seen.
There are too many assumptions that a large general-purpose model will be a one-size-fits-all. I don't buy it. The reality, and the research supports this, is that these different models show different strengths and capabilities.
Understanding how to tap into them in combination is a huge unlock. All engineering teams need to be thinking about this more carefully as a strategy going forward. Especially now, given the trends from frontier models in terms of selective access.
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
Notably, the budget panel was comparable with Claude Fable 5 in performance.
A panel of Gemini 3 Flash, Kimi K2.6, and DeepSeek V4 Pro, fused together, beat solo GPT-5.5 and solo Opus 4.8 outright.
And it landed within 1% of Fable 5 while costing roughly half the price.
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
How does it work?
When you send a prompt to Fusion, we fan it out to a panel of models in parallel, each with web search and bash tools enabled.
A judge model reads every response and extracts the structure: consensus points, contradictions, partial coverage, unique insights, blind spots.
Chatroom: https://openrouter.ai/fusion
Fusion is neurodiversity, but for models. Try it now!
💬 Chatroom: http://openrouter.ai/fusion (pick a preset or build a custom panel)
⚙️ API: docs at http://openrouter.ai/docs/guides/features/server-tools/fusion
ℹ️ More info on the blog post: https://openrouter.ai/blog/announcements/fusion-beats-frontier/
If you're a researcher looking to:
→ conduct rigorous studies on how multiple models can outperform the frontier → leverage data from the largest LLM marketplace (150+ trillion tokens processed per month)
... DM me with your work!
We have an exciting role coming in the future, but might fill it opportunistically.
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
We ran it on the DRACO deep research benchmark by Perplexity: 100 deep research tasks across 10 domains, from law and medicine to finance and product comparison.
Each task is graded against ~39 weighted criteria, and wrong answers carry negative weight. (You can't bluff your way to a high score by being verbose.)
https://arxiv.org/abs/2602.11685
By testing different combinations of models, we found that roughly three quarters of the lift that Fusion provides comes from synthesis, and one quarter from diversity.
Want to customize the panel? Pass your own participant models and synthesizer:
@OpenRouter Looks like something Hermes Agent users might like!
Then a synthesizer writes the final answer grounded in that analysis
Fusion runs server-side, so developers can call it exactly like a single model slug: "openrouter/fusion"
Or let the model decide when to reach for it by adding {"type": "openrouter:fusion"} to your tools array.
@YashasGunderia We ran these benchmarks earlier in the week, before Fable was taken down
@OpenRouter I believe the results!
Built an extension for VS Code that allows Claude and Codex to iterate back and forth and the results are mind blowing.
One detail we want to call out: when we first gave the panel web search, models started surfacing the DRACO rubric online.
We excluded those domains across every model with a one-line config change to the OpenRouter web search tool config, then re-ran everything. All published numbers come from the clean setup.
@IkeVictor Cost comparisons were performed including cache hits
@OpenRouter Whomever is interested in other workflows like that, you might find this collection very interesting: https://github.com/av/harbor/blob/main/docs/5.2.3-Harbor-Boost-Modules.md
@OpenRouter so what you're saying is...
@OpenRouter But fable is not available anymore
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
