Fugu Ultra
TL;DR
PremiumMulti-agent orchestration across frontier models.
Available on
Higher-tier model. Not on the Go or Pro plans.
Switch with
Pick Fugu Ultra from the selector.
Input
$5
per M tokens
Output
$30
per M tokens
Cache read
$0.50
per M tokens
Fugu Ultra in Command Code
Fugu Ultra is Sakana's closed-source orchestration model — instead of answering from a single model, it routes a task across a swappable pool of frontier models and coordinates them toward the result. It carries a 1M-token context and vision input. In Command Code it is a higher-tier premium model.
Fugu Ultra vs the Command Code lineup
Pricing for Fugu Ultra alongside the most relevant peers. Fugu Ultra is not yet on the Intelligence Index; benchmarked peers show their scores.
| Model | Intelligence | Speed | Input $/M | Output $/M |
|---|---|---|---|---|
| Fugu Ultra | Not yet scored | — | $5.00 | $30.00 |
| GPT-5.5 | 60 | ~65 tok/s | $5.00 | $30.00 |
| Claude Opus 4.7 | 57 | ~49 tok/s | $5.00 | $25.00 |
| GPT-5.4 | 57 | ~84 tok/s | $2.50 | $15.00 |
| Claude Sonnet 4.6 | 52 | ~62 tok/s | $3.00 | $15.00 |
| Kimi K2.6 | 54 | ~40 tok/s | $0.95 | $4.00 |
What Fugu Ultra is best for
Hard, open-ended tasks where orchestrating multiple frontier models beats any single one, and high-autonomy runs where you want the strongest available coordination.
When to switch away from Fugu Ultra
Switch to GPT-5.5
A single frontier model at the top of the Intelligence Index (60), cheaper on input.
Switch to Claude Opus 4.7 or GPT-5.4
Top-tier single models (Intelligence Index 57) when one model is enough.
Switch to Claude Sonnet 4.6
The recommended default for everyday work.
In Command Code: caching and taste-1
Two things change the experience of using this model inside Command Code versus calling it directly through the upstream API.
First, prompt caching is on by default. In an agent loop the same context is read across many steps; cache reads are billed at $0.50 per million tokens versus $5 for fresh input.
Second, taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Premium orchestration model. Available on Max 10× ($100/mo), Max 20× ($200/mo), Teams ($40/mo per seat), and Enterprise. Not on the Go or Pro plans.
All Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is reported output tokens per second. Models without a published score are noted.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| GPT-5.5 | Premium | 60 | ~65 tok/s |
| Claude Opus 4.7 | Premium | 57 | ~49 tok/s |
| GPT-5.4 | Premium | 57 | ~84 tok/s |
| GPT-5.3 Codex | Premium | 54 | ~72 tok/s |
| Kimi K2.6 | Open-source | 54 | ~40 tok/s |
| Claude Sonnet 4.6 | Premium | 52 | ~62 tok/s |
| DeepSeek V4 Pro | Open-source | 52 | ~35 tok/s |
| GLM-5 | Open-source | 50 | ~61 tok/s |
| GPT-5.4 Mini | Premium | 49 | ~164 tok/s |
| DeepSeek V4 Flash | Open-source | 47 | ~82 tok/s |
| Claude Haiku 4.5 | Premium | 37 | ~97 tok/s |
| Kimi K2.5 | Open-source | 37 | ~35 tok/s |
| Claude Sonnet 5 | Premium | Not yet scored | — |
| Claude Opus 4.8 | Premium | Not yet scored | — |
| Claude Opus 4.6 | Premium | Not yet scored | — |
| MiniMax M2.5 | Open-source | Not yet scored | — |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick the model you want and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick a modelPlans and pricing
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits. Credits roll over and never expire. Auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams | $40 / seat | Pooled | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Frequently asked questions
What does Fugu Ultra actually do?
It is an orchestration product: instead of one model answering, it routes across a pool of frontier models and coordinates them. The listed price is the base tier (context ≤272K); above that the upstream bills roughly 2×.
Which plans include Fugu Ultra?
Max 10×, Max 20×, Teams, and Enterprise. It is not available on the Go or Pro plans.
Which Command Code model should I use?
For open models, Kimi, DeepSeek, Qwen, Mimo are all really good. For closed models, Claude Sonnet 5 is the recommended default — the best combination of speed and intelligence, and a drop-in upgrade from Sonnet 4.6. Switch to Claude Opus 4.8 (the newest Anthropic flagship) for the most capable long-horizon agentic coding, GPT-5.5 (Intelligence Index 60) for the absolute hardest reasoning, or Claude Opus 4.7 / GPT-5.4 (both 57) for top-tier work at lower cost. For fast lookups, Claude Haiku 4.5 or GPT-5.4 Mini. For open-source, Kimi K2.6 leads the open-weights tier (Intelligence Index 54).
Can I mix Fugu Ultra with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep Sonnet 5 as the default and switch up to Opus 4.8 or down to Haiku 4.5 as the task calls for it.
Are open-source model prices fixed?
Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.