LLM Reference

Fugu

Released
2026-06-22
Last refreshed
2026-06-22
Status
Researched today
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Fugu is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Fugu
Released
2026-06-22
Context
1m
Architecture
Composition of Experts
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Reinforcement Learning
Created by

Nature-inspired AI foundation models.

Tokyo, Japan
Founded 2023
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Sakana AI

About

Fugu is Sakana AI's latency-optimized multi-agent orchestration model available via API. Internally, a trained coordinator model routes requests to specialist frontier LLMs in Thinker/Worker/Verifier roles. Supports text and image input. OpenAI SDK compatible (base_url: https://api.sakana.ai/v1). API model ID: fugu.

Fugu is a proprietary model. The structured metadata tracks a 1m-token context window, multimodal input, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through Sakana AI. Headline tracked benchmarks include SWE-bench Pro 59.0, Terminal-Bench 2.1 80.2, and LiveCodeBench 92.9.

Top use-case fit: coding, agents, and build tasks

Coding

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Sakana AI--
ServerlessPartial

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(6)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
SWE-bench Pro59.0SWE-bench Pro, Sakana AI-reportedhttps://sakana.ai/fugu/
Terminal-Bench 2.180.2Terminal-Bench 2.1, Sakana AI-reportedhttps://sakana.ai/fugu/
LiveCodeBench92.9LiveCodeBench, Sakana AI-reportedhttps://sakana.ai/fugu/
Google-Proof Q&A95.5diamondhttps://sakana.ai/fugu/
Humanity's Last Exam47.2Humanity's Last Exam, Sakana AI-reportedhttps://sakana.ai/fugu/
CharXiv85.1reasoninghttps://sakana.ai/fugu/

Migration checks

No linked migration route is available for this model yet.