
Fugu Ultra vs Kimi K2.7 · Fast
Sakana's multi-agent answer to Fusion — frontier ensemble without single-vendor risk. vs Fast mode — top speed, minimal thinking.
What I tested — same prompt, two models
I run the same fixed prompt set through every new model the day it drops — same string, one shot, single HTML file out — and I score the result 0–10 on whether it ran, how close it hit the brief, and how good it looked. Below is what came out when I gave the exact same prompts to Fugu Ultra and Kimi K2.7 · Fast, side by side, on 1 shared tasks inside the Agent Operating System.
Both models were given identical prompts inside the Agent Operating System — no help, no iteration, no "best of N" tricks. I run each prompt once, save the HTML file the model produces, and score it 0–10 on whether it ran, how close it hit the brief, and how good it looked. The scoring is mine. The verdicts below are pulled from my source comparison guides at agentos.guide where I publish every score and the reasoning behind it.
Fugu Ultra · Dispatched from Agent OS as the panel-ensemble alternative to OpenRouter Fusion. Bench scored by Claude judge against the same 42 prompts as every other model.
Kimi K2.7 · Fast · Wired into Agent OS as the snappy default — first-pass attempts, agent chatter, live demos.
Side-by-side on 7 shared tasks
Click any cell to play that model's actual one-shot attempt. Medals are derived from my 0–10 scores per task (highest = 🥇, second = 🥈, third = 🥉).
Strengths & weaknesses I logged
Fugu Ultra
Strengths
- SWE Bench Pro 73.7 · GPQA-D 95.5 · MRCRv2 93.6 — Sakana's published frontier-tier benchmark scores
- Vendor-agnostic ensemble — opt out of specific providers for compliance / export-control
- OpenAI-compatible API at api.sakana.ai — drop-in for existing tooling
Trade-offs
- Panel orchestration adds latency — even a 'pong' burns ~2k orchestration tokens
- Newer than Fusion; less community calibration on long-tail prompts
Kimi K2.7 · Fast
Strengths
- Lowest latency of the three Kimi modes for short builds
- Same 256K context as Quality mode
- Best when you need agent-loop responsiveness over polish
Trade-offs
- Skips deeper reasoning passes — bronze-tier on tasks needing planning
- Julian explicitly does not assign scores to Kimi modes on the standalone bench
Pricing & context — the spec sheet
| Spec | Fugu Ultra | Kimi K2.7 · Fast |
|---|---|---|
| Vendor | Sakana AI | Moonshot AI |
| Context window | 272,000 tokens with the standard rate. Calls exceeding 272K context are billed at the higher 'long-context' rates. | 256,000 tokens |
| Price | $5 / 1M input · $30 / 1M output (Fugu Ultra) | Flat plan (no per-token bill) |
| Pricing detail | Sakana's multi-agent orchestration: a single API call internally dispatches to multiple frontier models and synthesises the answer. Subscription plans run $20-$200/mo (Standard / Pro / Max); PAYG is $5/M input + $30/M output for Fugu Ultra. Direct competitor to OpenRouter Fusion's panel approach. | Same flat-rate plan as standard Kimi K2.7 — Fast mode is a runtime toggle, not a separate model. |
| Release | 2026-06-15 | 2026-06 |
| Bench coverage | 5/5 scored · avg 7.60/10 | 0/3 scored · avg — |
The verdict — which should you pick?
Not enough scored shared tasks yet for a head-to-head average. The live demos for both are on the matrix above — play them and form your own opinion.
If you only run one of these inside your stack, the head-to-head average above is the call. If you can run both, my honest play is to wire Fugu Ultra and Kimi K2.7 · Fast both into the Agent Operating System and dispatch each from the kanban by task type — teams that want fusion-class quality but need a different vendor risk profile → Fugu Ultra, snappy iteration inside agent loops → Kimi K2.7 · Fast. That's the same setup I run for the 3,600+ founders inside the AI Profit Boardroom.
FAQ — Fugu Ultra vs Kimi K2.7 · Fast
Which is better, Fugu Ultra or Kimi K2.7 · Fast?
On Goldie Bench, Fugu Ultra averages no scored verdicts yet across the shared tasks, with 3 gold, 1 silver, 0 bronze overall. Kimi K2.7 · Fast averages no scored verdicts yet, with 0 gold, 0 silver, 0 bronze. Not enough scored shared tasks yet to call a winner.
How much does Fugu Ultra cost vs Kimi K2.7 · Fast?
Fugu Ultra: Sakana's multi-agent orchestration: a single API call internally dispatches to multiple frontier models and synthesises the answer. Subscription plans run $20-$200/mo (Standard / Pro / Max); PAYG is $5/M input + $30/M output for Fugu Ultra. Direct competitor to OpenRouter Fusion's panel approach. Kimi K2.7 · Fast: Same flat-rate plan as standard Kimi K2.7 — Fast mode is a runtime toggle, not a separate model.
What's the context window for Fugu Ultra vs Kimi K2.7 · Fast?
Fugu Ultra has a 272,000 tokens with the standard rate. Calls exceeding 272K context are billed at the higher 'long-context' rates. context window. Kimi K2.7 · Fast has a 256,000 tokens context window.
When should I pick Fugu Ultra over Kimi K2.7 · Fast?
Pick Fugu Ultra for: Teams that want Fusion-class quality but need a different vendor risk profile; Operators avoiding export-controlled providers (Sakana emphasises this in their pitch); Deep-research workflows where ensemble verdicts beat single-model answers. The trade-off is the weaknesses we logged on the bench: Panel orchestration adds latency — even a 'pong' burns ~2k orchestration tokens; Newer than Fusion; less community calibration on long-tail prompts.
When should I pick Kimi K2.7 · Fast over Fugu Ultra?
Pick Kimi K2.7 · Fast for: Snappy iteration inside agent loops; Short prompts where Quality mode would over-think; Live demos where latency matters more than the last 5% of polish. The trade-off is the weaknesses we logged on the bench: Skips deeper reasoning passes — bronze-tier on tasks needing planning; Julian explicitly does not assign scores to Kimi modes on the standalone bench.
How does Goldie Bench score Fugu Ultra vs Kimi K2.7 · Fast?
Every demo on this page was built by Julian Goldie inside the Agent Operating System — same fixed prompt for both models, one shot, single HTML file out. Each result gets a 0–10 score on whether it ran, how close it hit the brief, and how good it looked. The highest score on each task gets gold; second gets silver; third gets bronze. See methodology for full provenance.
Related comparisons
Other head-to-heads using the same scoring system:
Fugu Ultra vs Opus 4.8 Kimi K2.7 · Fast vs Opus 4.8 Fugu Ultra vs GLM-5.2 Kimi K2.7 · Fast vs GLM-5.2 Fugu Ultra vs Grok Kimi K2.7 · Fast vs Grok Fugu Ultra vs Fusion Kimi K2.7 · Fast vs FusionFull model pages: Fugu Ultra · Kimi K2.7 · Fast · back to the leaderboard
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 3,600+ founders shipping with it every day all live inside the AI Profit Boardroom.






