Fugu Ultra
Sakana AI · released Jun 24, 2026
- Type
- Proprietary
- Input
- $5.00
- Output
- $30.00
- Cached
- $0.50
List price · per 1M tokens · Sakana AI at 1M context · source ↗
Our take
Written Aug 3, 2026Fugu Ultra is a proprietary multimodal model from Sakana AI that accepts text and images and can handle up to one million tokens in a single request. It is built for long-document and visual analysis tasks where extended reach matters more than measured leaderboard scores.
Choose this when you need to analyse entire books, large codebases or extended transcripts alongside images in one pass, and when Sakana's confirmed 32 tokens per second meets your latency needs. Skip it if you need independent quality verification, a local deployment path, or a choice of verified providers.
The case for it
- One-million-token request limit — ten times the threshold that defines long-context in most catalogues.
- Multimodal input combining images with very long text.
The case against it
- No benchmark scores in our data, so there is no independent quality verification for its premium output rate.
- Proprietary weights with no disclosed licence, leaving no local deployment or fine-tuning path.
- Throughput unverified on one of its two tracked providers.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Fugu Ultra — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Sakana AI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $5.00 in / $30.00 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $5.00 / $30.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Sakana AI | $5.00 / $30.00 | 1M | 66 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✓ |
| Sakana AI | ✓ | ✗ | ✓ |
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
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, 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 do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image->text
- Catalogue slug
- sakana-fugu-ultra