Fugu Ultra
Sakana AI · released Jun 24, 2026
- Type
- Closed
- Input
- $5.00
- Output
- $30.00
- Cached
- $0.50
List price · per 1M tokens · Sakana AI at 1M context · source ↗
Our take
Written Sep 2, 2026Fugu Ultra is Sakana AI's proprietary text-and-image model that can handle up to one million tokens in a single request. It is one of the longest-context options we track, though its speed and unverified quality make it a niche pick.
Choose this when you need very long document workflows and the one-million-token limit is the deciding factor, or for combined image-and-text tasks where you can tolerate slow responses. Skip it if throughput matters, if you need measured quality benchmarks, or if you want to self-host.
The case for it
- One-million-token request limit, among the longest context lengths we track.
- Flat pricing across both hosts, with no tiering to navigate.
The case against it
- Extremely slow on the only host that discloses speed, at three tokens per second.
- No benchmark scores in our data, so there is no measured quality data.
- Parameter count and architecture undisclosed by the lab.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Sakana AI, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Sakana AI on 1M of context.
- per 1M tokens
- $5.00 in / $30.00 out
- Context served
- 1M
- Throughput
- ~56 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $5.00 / $30.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Sakana AIThrough OpenRouter | $5.00 / $30.00checked 4 hours ago | 1M128K max reply | 56 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✓ |
| Sakana AIThrough OpenRouter | ✓ | ✗ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- sakana-fugu-ultra