Models.dev

An open-source database of AI models

Fugu Max

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

sakana/fugu-max
Lab
Sakana AI
Family
fugu
Providers
9
Context
1,000,000
Output limit
128,000
Knowledge
-
Release
2026-09-11
Updated
2026-09-11
Weights
Closed
Input
Output types
Capabilities
tools, reasoning

Providers

9
Providers
AI/ML APISakana AIsakana/fugu-max1,000,000128,000$2.116 / $6.348YesYesYesNo
DevPass (LLM Gateway)Sakana AIfugu-max1,000,0001,000,000$2.00 / $6.00YesYesYesYes
EmpirioLabs AISakana AIfugu-max1,000,000131,072$2.00 / $6.00YesYesYesNo
Kilo GatewaySakana AIsakana/fugu-max1,000,000128,000$2.00 / $6.00YesYesYesNo
LLM GatewaySakana AIsakana/fugu-max1,000,0001,000,000$2.00 / $6.00YesYesYesYes
Merge GatewaySakana AIsakana/fugu-max1,000,000128,000$2.00 / $6.00YesYesNoNo
NanoGPTSakana AIsakana/fugu-max1,000,000128,000$2.00 / $6.00YesYesYesNo
OpenRouterSakana AIsakana/fugu-max1,000,000128,000$2.00 / $6.00YesYesYesNo
Vercel AI GatewaySakana AIsakana/fugu-max1,000,0001,000,000$2.00 / $6.00YesYesYesNo
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

The homepage starts with provider-agnostic model metadata. Model pages list the providers serving that model; provider pages list every model available from that provider; lab pages group canonical models by author.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints. Specialized model types are omitted by default; the site includes all model types.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

SDK

Use the SDK to query the API from your app. It's type-safe and exports the latest snapshot for offline use.

Contribute

The data is stored in GitHub as TOML files organized by provider and canonical model.