AiCostCompare

Claude Sonnet 5 vs Fugu Ultra v2

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Fugu Ultra v2 (Sakana). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 11:56 AM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

Fugu Ultra v2

Sakana

Pricing
Input $/1M$2.00$5.00
Output $/1M$10.00$30.00
Blended $/1M (3:1)$4.00$11.25
RAG example (30K in / 2K out)$0.08$0.21
Quality & speed
Intelligence Index——
Coding Index71.5—
Agentic Index43.6—
Output speed (tok/s)——
Time to first token——
Specs
Context window1M1M
Input modalitiestext, image, filetext, image, file

FAQ

Which is cheaper, Claude Sonnet 5 or Fugu Ultra v2?

Claude Sonnet 5 has the lower blended API price at $4.00 per 1M tokens (3:1 input:output mix), versus $11.25 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Claude Sonnet 5 costs about $0.08 per request versus $0.21. Also compare context windows: Claude Sonnet 5 offers 1M and Fugu Ultra v2 offers 1M.

Which scores higher on Artificial Analysis benchmarks?

Intelligence Index scores are unavailable or tied for these two models. Compare coding index, speed, and price on this page to decide.