LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
sa

Fugu Ultra

sakana·sakana/fugu-ultra·GA·Closed·fugu series
Quality-first multi-agent model for hard research, analysis, and competitions

Specs & pricing

Input / output per 1M tokens
Official price·Sakana AI
$5.00 / $30.00
Blended $11.25 · Cache read $0.50
Lowest paid·Sakana AIFirst-party
$5.00 / $30.00
Blended $11.25 · 1.5× spread
Context
1,000,000
Output limit
1,000,000
Knowledge cutoff
—
Released / updated
2026-06-15 / 2026-06-15
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImage
References
Official model catalog

Fugu Ultra by sakana is offered by 15 providers on this page. Its official list price is $5.00 per 1M input tokens and $30.00 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 1.5× across the providers that host it.

The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image.

Available at 15 providers15 with public prices

  • ProviderInput / Output
  • Sakana AIOfficialFirst-party
    fugu-ultra-20260615
    $5.00 / $30.00
    tiered >272K: $10.00
    Cache read $0.50Context 1,000,000Output limit 1,000,000
  • Sakana AIOfficialFirst-party
    $5.00 / $30.00
    tiered >272K: $10.00
    Cache read $0.50Context 1,000,000Output limit 1,000,000
  • LLM GatewayGateway
    $5.00 / $30.00
    Cache read $0.50Context 1,000,000Output limit 1,000,000
  • CommandCodeGateway
    $5.00 / $30.00
    Cache read $0.50Context 1,000,000Output limit 128,000
  • RequestyGateway
    $5.00 / $30.00
    tiered >272K: $10.00
    Cache read $0.50Context 1,048,576 ⚠Output limit 131,072
  • NanoGPTGateway
    $5.00 / $30.00
    Cache read $0.50Context 1,000,000Output limit 16,384
  • DevPass (LLM Gateway)Gateway
    $5.00 / $30.00
    Cache read $0.50Context 1,000,000Output limit 1,000,000
  • Merge GatewayGateway
    $5.00 / $30.00
    tiered >272K: $10.00
    Cache read $0.50Context 1,000,000Output limit 128,000
  • OpenRouterGateway
    $5.00 / $30.00
    tiered >272K: $10.00
    Cache read $0.50Context 1,000,000Output limit 128,000
  • LLMTRGateway
    $5.00 / $30.00
    Cache read $0.50Context 1,000,000Output limit 1,000,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Sakana AIOfficial
fugu-ultra-20260615
First-party$5.00
tiered >272K: $10.00
$30.00$0.50—1,000,0001,000,000
Sakana AIOfficialFirst-party$5.00
tiered >272K: $10.00
$30.00$0.50—1,000,0001,000,000
LLM GatewayGateway$5.00$30.00$0.50—1,000,0001,000,000
CommandCodeGateway$5.00$30.00$0.50—1,000,000128,000
RequestyGateway$5.00
tiered >272K: $10.00
$30.00$0.50—1,048,576 ⚠131,072
NanoGPTGateway$5.00$30.00$0.50—1,000,00016,384
DevPass (LLM Gateway)Gateway$5.00$30.00$0.50—1,000,0001,000,000
Merge GatewayGateway$5.00
tiered >272K: $10.00
$30.00$0.50—1,000,000128,000
OpenRouterGateway$5.00
tiered >272K: $10.00
$30.00$0.50—1,000,000128,000
LLMTRGateway$5.00$30.00$0.50—1,000,0001,000,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = higheffort = xhigheffort = maxeffort = noneeffort = loweffort = medium

Your usage cost

Common scenarios
1Sakana AI · Official$1,960.00
2Sakana AI · Official$1,960.00
3LLM Gateway$1,960.00
4CommandCode$1,960.00
5Requesty$1,960.00
6NanoGPT$1,960.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$30.00$02026-08-052026-08-28
2026-08-28Input list $5.00Output list $30.00Min blended $11.25

Benchmark12 items

NameConditionsScoreMetricSource
SWE Bench Pro—73.7—Source ↗
Terminal Bench 2.1—82.1—Source ↗
LiveCodeBench—93.2—Source ↗
LiveCodeBench Pro—90.8—Source ↗
Humanity’s Last Exam—50—Source ↗
CharXiv Reasoning—86.6—Source ↗
GPQA Diamond—95.5—Source ↗
SciCode—58.7—Source ↗
τ3 Banking—20.6—Source ↗
Long Context Reasoning—73.3—Source ↗
MRCRv2—93.6—Source ↗
CTI-REALM—69.4—Source ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

saFugu Maxsame series—saFugu Ultra v2same series—saFugu Ultra v2.0same series—GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40
Data partly from models.dev (MIT) · Sakana AI official docs ↗