openai
Fugu Ultra vs GPT-5.5
80.2 overall · $11.25 / 1M
// sakana
Fugu Ultra
sakana/fugu-ultra
reasoningtool callingimage inputprompt caching
Fugu Ultra costs $5.00 per 1M input tokens and $30.00 per 1M output tokens with a 1M-token context window.
A reasoning, tool-calling model from sakana, released Jun 24, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $5.00
- Output / 1M
- $30.00
- Context
- 1M
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $5.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $30.00 |
| Blended price 3:1 input:output — #15 most expensive of 343 listed models | $11.25 |
| Cached input read Blank means not priced separately — not free | $0.500 |
| Cache write | — |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Input modalities | text, image |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jun 24, 2026 |
What Fugu Ultra costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $3,276/mo |
| RAG assistant 8K in / 600 out × 100K requests | $4,000/mo |
| Coding agent 40K in / 4K out × 20K requests | $3,880/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $7,025/mo |
| Bulk classification 500 in / 20 out × 5M requests | $13,250/mo |
Compare Fugu Ultra with
Benchmarked models at a similar price.
anthropic
Fugu Ultra vs Claude Opus 5
80.1 overall · $10.00 / 1M
anthropic
Fugu Ultra vs Claude Opus 4.8
76.2 overall · $10.00 / 1M
anthropic
Fugu Ultra vs Claude Opus 4.7
76.5 overall · $10.00 / 1M
anthropic
Fugu Ultra vs Claude Opus 4.6
74.5 overall · $10.00 / 1M
anthropic
Fugu Ultra vs Claude Opus 4.5
72.6 overall · $10.00 / 1M
Fugu Ultra FAQ
How much does Fugu Ultra cost?
Fugu Ultra lists at $5.00 per 1M input tokens and $30.00 per 1M output tokens, with cached input reads at $0.500 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $4,000 at list price.
What is the context window of Fugu Ultra?
Fugu Ultra accepts up to 1,000,000 tokens of context and can return up to 128,000 output tokens per response.
Does Fugu Ultra support tool calling?
Yes — Fugu Ultra supports tool (function) calling and exposes extended reasoning. It accepts text, image input.
How does Fugu Ultra score on benchmarks?
LiveBench has not published a run for Fugu Ultra yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Fugu Ultra?
On OpenRouter the model ID is "sakana/fugu-ultra". It was listed on Jun 24, 2026.
More from sakana
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.