Providers and ModelsSakana AI

Fugu Ultra v2.0

Fugu Ultra v2.0
Sakana AI · Text Generation
POST /v1/chat/completions

Flagship multi-agent conductor for the hardest reasoning, coding, and research work, with 1M context, image input, and web search.

At a glance

FieldValue
Model idfugu-ultra-v2-0
Model release date2026-09-10
Input modalitiesText, Image
Output modalitiesText
Context window1M
Weight precision-
Max output tokens131,072
Featuresreasoning, multimodal, web_search, function_calling, agentic_coding, structured_output, cache
Native inferenceNo
NewYes
Structured outputJSON Schema
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/fugu-ultra-v2-0:generateContent
Alternate model idsfugu-ultra-v2.0, sakana/fugu-ultra-v2-0, sakana/fugu-ultra-v2.0

Pricing

ChargeSpecRate
Inputper 1M prompt tokens<=272K $5.00; >272K $10.00
Outputper 1M generated tokens<=272K $30.00; >272K $45.00
Implicit cache readper 1M cached input tokens<=272K $0.50; >272K $1.00

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "fugu-ultra-v2-0", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
max_tokensintegerno32768Maximum number of output tokens for the final answer. Must be at least 16. The conductor needs room to work, so very small values can truncate or empty the answer. · Range: 16 – 131072
reasoning_effortenumno"high"How hard Fugu Ultra v2.0 reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort. · Allowed: high, xhigh, max
tool_web_searchbooleannofalseEnable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request.
toolsarrayno[]OpenAI-compatible function calling tool definitions.
tool_choiceobjectno-OpenAI-compatible tool choice control.
response_formatenumno-Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces the exact schema you provide.

Notes

Fugu Ultra v2.0 is the flagship 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 raises the effort, and max is accepted as an alias of xhigh.
  • Function calling, strict JSON Schema structured output, and built-in web search that cites its sources when available (no separate fee).

Versioning

  • Use fugu-ultra-v2-0 for v2.0. The legacy fugu-ultra id remains pinned to v1.0 for backward compatibility, and fugu-ultra-v1-1 continues to serve v1.1.

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.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/fugu-ultra-v2-0.