Sakana AI Models
Tokyo-based AI research lab building nature-inspired, multi-model systems (Fugu family). Retains API prompts but does not train on them. Requesty routes to 1 Sakana AI model starting at $5.00 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
All Sakana AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
fugu-ultra | 1.0M | 131K | $5.00 | $30.00 | 🔧⚡ | N/A |
About Sakana AI on Requesty
How many Sakana AI models are available through Requesty?
Requesty routes to 1 Sakana AI model including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Sakana AI model?
The cheapest Sakana AI model starts at $5.00 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Sakana AI pricing?
No. Requesty passes through exactly what Sakana AI charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Sakana AI models?
Sakana AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Sakana AI models hosted?
Sakana AI models are hosted in 🇯🇵 Japan. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Sakana AI rows in the models explorer.