AI Models · Paid vs Paid

SAFugu Ultra v2 Paid vs SCExtract Paid

Fugu Ultra v2 vs Extract compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.

Fugu Ultra v2 — full profile ›  ·  Extract — full profile ›

Prices & specs refreshed from live data · olud.ai

Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.

SAFugu Ultra v2PaidSakana AI
$5 /M input
$30 /M outputManaged API (no infra to run)
TypeProprietary
Context window1M tokens
MultimodalYes
Self-hostNo
SCExtractPaidScaledown
$0.04 /M input
Free /M outputManaged API (no infra to run)
TypeProprietary
Context window1M tokens
MultimodalYes
Self-hostNo
Choose Extract for the lower output price (Free/M vs $30/M). Choose Fugu Ultra v2 if you need the larger 1M context window.

Fugu Ultra v2 vs Extract specs

SpecFugu Ultra v2ExtractWinner
MakerSakana AIScaledown–
TypeProprietaryProprietary–
Context window1M tokens1M tokens= Tie
Input price$5/M$0.04/MSCExtract
Output price$30/MFree/MSCExtract
Vision / multimodalYesYes= Tie
Tool / function callingYesNoSAFugu Ultra v2
Self-hostableNo (API only)No (API only)–
LicenseProprietaryProprietary–

Price gap & when to choose each

SAChoose Fugu Ultra v2 if…
  • You want frontier performance through a managed API
  • You value reliability & ecosystem
  • You don't want to manage infrastructure
SCChoose Extract if…
  • You want frontier performance through a managed API
  • You want the lower output price
  • You value reliability & ecosystem
  • You don't want to manage infrastructure

Feature comparison

CapabilityFugu Ultra v2Extract
Open weights (downloadable)✗✗
Self-hostable✗✗
Runs fully offline✗✗
Vision / multimodal✓✓
Tool / function calling✓✗
1M+ context window✓✓

How Fugu Ultra v2 and Extract score

🤝 Neck and neck on these criteria (3.1 vs 3.2 / 5).
CriterionFugu Ultra v2Extract
Cost-efficiency3.05.0
Context window5.05.0
Openness1.51.5
Self-hosting1.01.0
Multimodality5.03.5

Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.

What each model is

Fugu Ultra v2 Paid

Sakana AI · Proprietary

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...

Extract Paid

Scaledown · Proprietary

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...

Frequently asked questions

Fugu Ultra v2 vs Extract — which is cheaper?

Extract is cheaper on output (Free/M vs $30/M).

Which has the larger context window?

Fugu Ultra v2 offers the larger context window (1M tokens).

Fugu Ultra v2 vs Extract — which should I pick in 2026?

Choose Extract for the lower output price (Free/M vs $30/M). Choose Fugu Ultra v2 if you need the larger 1M context window.

People also compare

DeepSeek V4.1 Flash 1017 vs Fugu Ultra v2DeepSeek V4.1 Flash 1017 vs ExtractGLM 5.3 (batch) vs Fugu Ultra v2GLM 5.3 (batch) vs ExtractHy3 vs Fugu Ultra v2Hy3 vs Extract

Explore more open-source AI

Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.

Open the leaderboard →