Fugu Ultra v1.0 API

Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.

Sakana AI Text Generation 1M context Released Jun 21, 2026 Proprietary Endpoint

About Fugu Ultra v1.0

Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.

Supports text and image input, a 1M token context, function calling, JSON mode structured output, and built-in web search. Reasoning is always on with effort levels high, xhigh, and max; xhigh and max are aliases on v1.0. Web search has no separate fee. Full orchestration token usage is billed at the displayed input, output, and cache rates.

Also known as Fugu Ultra, Sakana AI Fugu Ultra v1.0

reasoning multimodal web search function calling agentic coding cache

Fugu Ultra v1.0 specs

Model ID
fugu-ultra-v1-0
Author
Sakana AI
Category
Text Generation
Released
Jun 21, 2026
Context window
1M tokens
Max output
131,072 tokens
Input
TextImage
Output
Text
Structured output
JSON Mode
Endpoints
POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/fugu-ultra-v1-0:generateContent
Alternate model IDs
fugu-ultrafugu-ultra-20260615fugu-ultra-v1.0sakana/fugu-ultrasakana/fugu-ultra-20260615sakana/fugu-ultra-v1-0sakana/fugu-ultra-v1.0

Fugu Ultra v1.0 API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Input
per 1M prompt tokens
<=272K $7.50 >272K $15.00
Output
per 1M generated tokens
<=272K $45.00 >272K $67.50
Implicit cache read
per 1M cached input tokens
<=272K $1.50 >272K $3.00
Compare on the full pricing page

How to call the Fugu Ultra v1.0 API

Fugu Ultra v1.0 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id fugu-ultra-v1-0. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fugu-ultra-v1-0",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="fugu-ultra-v1-0",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full Fugu Ultra v1.0 API reference

Fugu Ultra v1.0 API parameters

Request parameters supported by the Fugu Ultra v1.0 API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
max_tokensinteger-16 to 131072Maximum number of output tokens for the final answer. Must be at least 16. Very small values can truncate or empty the answer. When omitted, the model's own default...
reasoning_effortenumhighhigh, xhigh, maxHow hard the model reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort.
tool_web_searchbooleanfalse-Enable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request.
toolsarray[]-OpenAI-compatible function calling tool definitions.
tool_choiceobject--OpenAI-compatible tool choice control.
response_formatenum--Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.

Good to know

Fugu Ultra v1.0 is the original multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.

Latency and streaming

  • Responses can take from a few seconds to a few minutes on complex prompts.
  • The full answer is returned all at once when the model finishes, not token by token. Streaming is accepted, but it delivers the complete response at the end rather than streaming tokens as they generate.
  • max_tokens must be at least 16. Leave generous headroom, since very small limits can truncate or empty the answer.

Capabilities

  • Text and image input, with a 1M token context.
  • Always-on reasoning. high is the default; xhigh and max are aliases of the same maximum effort.
  • Function calling, JSON mode, and built-in web search that cites its sources when available (no separate fee).

Compatibility

  • The legacy fugu-ultra, fugu-ultra-20260615, and sakana/fugu-ultra ids remain pinned to this version.

Billing

  • Billed on full token usage, including the orchestration tokens the model uses internally, so even short prompts carry some cost.
  • Context-tiered: requests above 272K total input tokens use the higher rate shown.

Fugu Ultra v1.0 on the blog

Announcements, prompt tests, and comparisons that cover this model.

Fugu Ultra v1.0 API: common questions

How much does the Fugu Ultra v1.0 API cost?

On EmpirioLabs, Fugu Ultra v1.0 is billed pay as you go. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does Fugu Ultra v1.0 support?

Fugu Ultra v1.0 takes Text, Image as input and returns Text.

What is the context window of Fugu Ultra v1.0?

Fugu Ultra v1.0 supports a 1M-token context window with up to 131,072 output tokens per response.

Is the Fugu Ultra v1.0 API OpenAI-compatible?

Yes. Fugu Ultra v1.0 serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to fugu-ultra-v1-0.

What is the model ID for Fugu Ultra v1.0?

Send fugu-ultra-v1-0 as the model in your request. The alternate IDs fugu-ultra, fugu-ultra-20260615, fugu-ultra-v1.0, sakana/fugu-ultra, sakana/fugu-ultra-20260615, sakana/fugu-ultra-v1-0, sakana/fugu-ultra-v1.0 also work.

When was Fugu Ultra v1.0 released?

Sakana AI released Fugu Ultra v1.0 on Jun 21, 2026.

Can I try Fugu Ultra v1.0 in the browser before integrating?

Yes. The EmpirioLabs playground runs Fugu Ultra v1.0 in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Fugu Ultra v1.0 API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare Fugu Ultra v1.0 with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.