Sakana AI: Fugu Ultra v2.0
Fugu Ultra v2.0 is a reasoning model from Sakana AI released on Jun 15, 2026. It reads text and images and writes text, with a 1M token context window and up to 131K tokens per reply.
Show moreShow less
It costs $5 per million input tokens and $30 per million output tokens. Cached input bills at $0.50, 90% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
3 providers serve it, including DevPass (LLM Gateway), EmpirioLabs AI and LLM Gateway.
- Modalities
- In / out price
- $5 / $30 per 1M
- Context
- 1M
- Max output
- 131K
- Released
- Jun 15, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Fugu Ultra v2.0 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $5 / 1M tokens | |
|---|---|---|
| Output | $30 / 1M tokens | |
| Cached input (read) | $0.50 / 1M tokens | 90% off input |
| Prompts over 200K | $10 in, $45 out | long context rate |
| Prompts over 272K | $10 in, $45 out | long context rate |
Fugu Ultra v2.0 providers
3 providers serve it, including DevPass (LLM Gateway), EmpirioLabs AI and LLM Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| DevPass (LLM Gateway) | $5 | $30 | $0.50 | 1M | 1M |
| EmpirioLabs AI | $5 | $30 | $0.50 | 1M | 131K |
| LLM Gateway | $5 | $30 | $0.50 | 1M | 1M |
What Fugu Ultra v2.0 costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Fugu Ultra v2.0 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to Fugu Ultra v2.0
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 26
Reads text, images and files. Tool calling, structured output, reasoning. Served by 46 providers.
by openaiMar 5, 20261.05M context$5/M input tokens$30/M output tokens46 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 36 providers.
by anthropicJul 23, 2026$5/M input tokens$25/M output tokens36 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 46 providers.
by anthropicMay 28, 2026$5/M input tokens$25/M output tokens46 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 44 providers.
by anthropicApr 14, 2026$5/M input tokens$25/M output tokens44 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 40 providers.
by anthropicFeb 1, 2026$5/M input tokens$25/M output tokens40 providers
- 200K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 29 providers.
by anthropicNov 1, 2025$5/M input tokens$25/M output tokens29 providers
More from Sakana AI
- 1M context
Reads text and images. Tool calling, structured output, reasoning. Served by 8 providers.
by sakanaSep 11, 2026$2/M input tokens$6/M output tokens8 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 3 providers.
by sakanaSep 11, 2026$5/M input tokens$30/M output tokens3 providers
- 262K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 4 providers.
by sakanaAug 3, 2026$0.95/M input tokens$4/M output tokens4 providers
- 1M context
Reads text and images. Tool calling, structured output, reasoning.
by sakanaJun 15, 2026
- 1M context
Reads text and images. Tool calling, structured output, reasoning. Served by 12 providers.
by sakanaJun 15, 2026$5/M input tokens$30/M output tokens12 providers
- 1M context
Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.
by sakanaJun 15, 2026$5/M input tokens$30/M output tokens2 providers
Fugu Ultra v2.0 questions
How much does the Fugu Ultra v2.0 API cost?
$5 per million input tokens and $30 per million output tokens, with cached input at $0.50. Prompts over 200K tokens bill at $10 input and $45 output. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Fugu Ultra v2.0?
1,000,000 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Fugu Ultra v2.0?
3 providers serve it, including DevPass (LLM Gateway), EmpirioLabs AI and LLM Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Fugu Ultra v2.0 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Fugu Ultra v2.0 open source?
No. Sakana AI serves it through an API only, so you cannot download the weights or host it yourself.
When was Fugu Ultra v2.0 released?
Jun 15, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.