Fugu

Sakana AIMCP Tool CallReasoning

sakana/fuguClosed API

Multi-agent model for routing expert agents across complex analytical tasks

Benchmark Pricing$5.00 / 1M in$30.00 / 1M out$0.50 cache read

Context: 1,000,000 tokens•Max Output: 4,096 tokens•Released: 2026-06-15

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens

Max Output4,0964.1K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVision

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Fugu natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

SWE Bench ProUnit not reported

Terminal Bench 2.1Unit not reported

80.2

LiveCodeBenchUnit not reported

92.9

LiveCodeBench ProUnit not reported

87.8

Humanity’s Last ExamUnit not reported

47.2

CharXiv ReasoningUnit not reported

85.1

GPQA DiamondUnit not reported

95.5

SciCodeUnit not reported

60.1

τ3 BankingUnit not reported

21.7

Long Context ReasoningUnit not reported

74.7

MRCRv2Unit not reported

86.6

CTI-REALMUnit not reported

67.5

API CALL INVOCATION EXAMPLE

// Example: Calling Fugu via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SAKANA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "sakana/fugu",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);