Sakana

9 indexed models

9 matching models

fugu-max

cheaperInference/fugu-max

Context window
1,000,000
Maximum output
1,000,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Inference prices

Fugu Max

vercelAIGatewayCatalog/sakana/fugu-max

Fugu Max orchestrates our largest pool of models to push the cost–performance Pareto frontier. It dynamically finds efficient combinations of expert agents, aiming to improve model performance and cost efficiency together.

Context window
1,000,000
Maximum output
1,000,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

fugu-ultra-v2

cheaperInference/fugu-ultra-v2

Context window
1,000,000
Maximum output
1,000,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Inference prices

Fugu Ultra v2

vercelAIGatewayCatalog/sakana/fugu-ultra-v2

Fugu Ultra coordinates a deeper pool of expert agents to maximize answer quality on hard, high-stakes problems. Fugu Ultra focuses on maximizing performance, for a higher cost.

Context window
1,000,000
Maximum output
1,000,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

Sakana: Fugu Max

sakana/fugu-max-20260911

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a fixed pool of open-weights and specialized models, including NVIDIA's Nem

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.25 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $2.00 / input_tokens_per_million · openRouter ↗
  • Published price : $6.00 / output_tokens_per_million · openRouter ↗

Sakana: Fugu Ultra

sakana/fugu-ultra-20260615

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances

Context window
1,000,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.50 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $5.00 / input_tokens_per_million · openRouter ↗
  • Published price : $30.00 / output_tokens_per_million · openRouter ↗

Sakana: Fugu Ultra v2

sakana/fugu-ultra-v2-20260911

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a fixed pool of open and specialized models and to recursively call

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.50 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $5.00 / input_tokens_per_million · openRouter ↗
  • Published price : $30.00 / output_tokens_per_million · openRouter ↗

Sakana Namazu

vercelAIGatewayCatalog/sakana/namazu

Sakana Namazu is a Japanese-specialized LLM that combines a deep understanding of Japanese culture and business customs with high-performance language capabilities. Built on the open model Kimi K2.6 and refined with Sakana AI's in-house data for Japanese language and business wor

Context window
256,000
Maximum output
256,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Inference prices

Sakana: Sakana Namazu

sakana/namazu-20260811

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following, business writing, mathematics, coding, research, and multi-step agent

Context window
262,144
Input modalities
text, image, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.15 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.95 / input_tokens_per_million · openRouter ↗
  • Published price : $4.00 / output_tokens_per_million · openRouter ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace