Sakana: Fugu Max V1.0
sakana/fugu-max-v1.0
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 Nemotron family, and to recursively call instances of itself. Fugu Max dynamically selects efficient combinations of expert agents to improve quality and cost together, and is priced flat regardless of context length. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search and web fetch. Orchestration tokens consumed by the system are billed as standard input/output tokens.
Model specifications
- Input
- text, image, file
- Output
- text
- Context
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input price
- $2 / 1M tokens
- Output price
- $6 / 1M tokens
- Released
- 2026-09-12
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $2 / 1M tokens · tier output average $6 / 1M tokens
Sakana Fugu
Tier: Standard · Region: JP
Pricing
- Input
- $2 / 1M tokens
- Output
- $6 / 1M tokens
- Cache read
- $0.25 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- JP
- Zero data retention
- No
- Data retention
- Unknown retention
- Used for training
- Unknown
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Frequently asked questions
- What is Sakana: Fugu Max V1.0?
- 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 Nemotron family, and to recursively call instances of itself. Fugu Max dynamically selects efficient combinations of expert agents to improve quality and cost together, and is priced flat regardless of context length. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search and web fetch. Orchestration tokens consumed by the system are billed as standard input/output tokens.
- How much does Sakana: Fugu Max V1.0 cost?
- Input costs start at $2 / 1M tokens and output costs start at $6 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Sakana: Fugu Max V1.0?
- Sakana: Fugu Max V1.0 supports a 1,000,000 token context window and up to 128,000 output tokens.
- What capabilities does Sakana: Fugu Max V1.0 support?
- Sakana: Fugu Max V1.0 supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer Sakana: Fugu Max V1.0?
- Sakana: Fugu Max V1.0 is available from Sakana Fugu.
- How do providers handle data privacy for Sakana: Fugu Max V1.0?
- 1 of 1 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.