Skip to content
ModelCap

Head-to-head comparison

Relace Search vs Fugu Ultra

Relace Search (Relace) and Fugu Ultra (Sakana AI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 17 August 2026

As of 17 August 2026, Relace Search holds the stronger ModelCap Index position (#155 vs #156); Relace Search is 10× cheaper per output token ($3.00/1M vs $30.00/1M); and Fugu Ultra offers the longer context window (1M vs 256K tokens).

Which should you choose?

Choose Relace Search if…

  • you want the stronger overall ModelCap Index position — #155 against #156 (22.5 vs 22.5 points).
  • API cost matters — $3.00/1M output tokens against $30.00/1M, about 10× cheaper.
  • your workload is prompt-heavy — input tokens cost $1.00/1M against $5.00/1M.

Choose Fugu Ultra if…

  • you need the longer context window — 1M tokens against 256K.
  • you want the more recently listed model — Fugu Ultra was listed 24 June 2026, Relace Search 8 December 2025.

Relace Search vs Fugu Ultra: specs, pricing and context

Specification comparison of Relace Search and Fugu Ultra
FieldRelace SearchRelaceFugu UltraSakana AI
ModelCap Index position#155#156
Index score22.522.5
EvidenceEstimatedEstimated
Input price / 1M tokens$1.00$5.00
Output price / 1M tokens$3.00$30.00
Context window256K tokens1M tokens
Max output tokens128K128K
API providers listed11
Weight accessAPI onlyAPI only
Input modalitiesTextText, Image
First listed8 December 202524 June 2026
PublisherRelaceSakana AI

Evidence: global corpus prior · leave-one-anchor-out calibrated · global corpus prior · leave-one-anchor-out calibrated. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Relace Search vs Fugu Ultra

Neither model has a published result on a public benchmark board ModelCap tracks yet.

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Relace Search vs Fugu Ultra: common questions

Is Relace Search better than Fugu Ultra?

Relace Search ranks higher on the ModelCap Index as of 17 August 2026: #155 against #156. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it.

Is Relace Search cheaper than Fugu Ultra?

Relace Search is cheaper on output tokens: $3.00/1M against $30.00/1M. Input tokens are $1.00/1M for Relace Search and $5.00/1M for Fugu Ultra. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Relace Search or Fugu Ultra?

Fugu Ultra has the larger context window: 1M tokens against 256K.

Which is better for coding, Relace Search or Fugu Ultra?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Relace Search and Fugu Ultra open-weight models?

Relace Search: API only. Fugu Ultra: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Relace Search and Fugu Ultra?

ModelCap currently lists 1 API provider for Relace Search and 1 for Fugu Ultra, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Relace Search vs Fugu Ultra comparison?

Every figure comes from the sealed ModelCap dataset published 17 August 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further