Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for sakana

Sakana: Fugu Ultra v2

sakana/fugu-ultra-v2

Compare

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 instances of itself.

Fugu Ultra v2 prioritizes answer quality on complex multi-step reasoning, autonomous research, and full-stack software development, and does not rely on individual proprietary frontier models in its pool. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search. Prompts above 272K tokens are billed at a higher rate. Orchestration tokens consumed by the system are billed as standard input/output tokens.

Modalities
In / Out Price
$5 / $30per 1M
Context
1.0M
Released
Sep 11, 2026
Knowledge Cutoff
Aug 2026
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$5.00$30.00$0.505.20s11 tps
100.00%
Throughput
11tok/s

P50, best across providers

Latency
5.20s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
85.12%

Availability over the last 3 days

Last 72 hours
Availability 85.12%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
86.12%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
565Mtokens
2.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
533Mtokens
3.
Favicon for https://omp.sh/
omp
new
125Mtokens
4.
Favicon for https://openai.com/codex
Codex
A coding agent that helps you build and ship with AI
77.6Mtokens
5.
Favicon for https://aside.com/
Mono Studio visual expansion
new
38.7Mtokens

Frequently asked questions

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 instances of itself.

Fugu Ultra v2 costs $5.00/M input tokens and $30.00/M output tokens, with separate rates for Cache Read at $0.50/M tokens and Web Search at $10.00/1K calls.

Fugu Ultra v2 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.

Yes. Fugu Ultra v2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Fugu Ultra v2 accepts text, images, and files such as PDFs as input and returns text.

Fugu Max, Sakana Namazu, and Fugu Ultra are other text models from Sakana.

Fugu Ultra v2 was released on September 11, 2026. Its knowledge cutoff is August 28, 2026.

More models from sakana

Fugu Max

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.

Text1M context$2 / $6
Sakana Namazu

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 workflows.

Sakana AI may use inputs for model training and improvement by default, with an opt-out available in the Sakana Console. Processing entirely within Japan is not guaranteed.

Text262K context$0.95 / $4
Fugu Ultra

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 of itself.

Fugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.

Text1M context$5 / $30