BuildLearnCommunity ModelsCheapestCoding Long-contextBest value API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › sakana › Sakana: Fugu Ultra v2

Sakana: Fugu Ultra v2 — pricing & benchmarks

By sakana · Updated 2026-07-24 · long-context / RAGvision / documentsstep-by-step reasoning

Sakana: Fugu Ultra v2 costs $5 per 1M input tokens and $30 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, vision / documents, step-by-step reasoning, and is available through one OpenAI-compatible Appmo API key.
$5Input / 1M
$30Output / 1M
1MContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What Sakana: Fugu Ultra v2 is used for

Sakana: Fugu Ultra v2 is best suited for long-context / RAG, vision / documents, step-by-step reasoning. Access it through one Appmo API key alongside 439 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"sakana/fugu-ultra-v2","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Sakana: Fugu Ultra v2 cost?
Sakana: Fugu Ultra v2 costs $5 per 1M input tokens and $30 per 1M output tokens ($11.25 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is Sakana: Fugu Ultra v2 best for?
Sakana: Fugu Ultra v2 is best suited for long-context / RAG, vision / documents, step-by-step reasoning.

How do I use Sakana: Fugu Ultra v2?
Send requests to Appmo's OpenAI-compatible endpoint with model id "sakana/fugu-ultra-v2" and one API key — no separate provider account needed.