sakana logo
sakana

Sakana: Fugu Ultra

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. $5 per million input tokens, $30 per million output tokens. 1,000,000 token context window, maximum output of 128,000 tokens.

Overview

Model specifications

Context
1,000,000 tokens
Maximum output
128,000 tokens
Architecture
text+image->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$5
/M tokens
  • ≤272K$5
  • >272K$10
Output
$30
/M tokens
  • ≤272K$30
  • >272K$45
Cache read
$0.5
/M tokens
  • ≤272K$0.5
  • >272K$1
Web search
$10
/1K calls
API

Model configuration

Reasoning

Moderated
Yes
Default parameters
xhigh
Capabilities
max, xhigh, high
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

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

InputOutput

Input
textimage
Output
text
Reasoning

Yes · max · xhigh · high

API

Supported API parameters

include_reasoningreasoningreasoning_effortstructured_outputstool_choicetoolsweb_search_options
Available providers

1 Provider

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Sakana AI

unknown
Context
1M
Maximum output
128K
Input
$5.00
Output
$30.00
Cache read
$0.500
Cache write
Not provided
sakana

models

All models