LLM Pricing
PricingLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
sa

Fugu Max

sakana·sakana/fugu-max·GA·Closed·fugu series·NEW
Multi-agent model for routing expert agents across complex analytical tasks

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·DevPass (LLM Gateway)Gateway
$2.00 / $6.00
Blended $3.00 · 1.1× spread
Context
1,000,000
Output limit
128,000
Knowledge cutoff
—
Released / updated
2026-09-11 / 2026-09-11
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImagePDF

Fugu Max by sakana is offered by 9 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is DevPass (LLM Gateway) at $2.00 / $6.00 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 1,000,000 tokens, with an output limit of 128,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF.

Available at 9 providers9 with public prices

  • ProviderInput / Output
  • DevPass (LLM Gateway)Gateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 1,000,000
  • OpenRouterGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 128,000
  • LLM GatewayGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 1,000,000
  • Kilo GatewayGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 128,000
  • EmpirioLabs AIGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 131,072
  • Vercel AI GatewayCloud
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 1,000,000
  • Merge GatewayGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 128,000
  • NanoGPTGateway
    $2.00 / $6.00
    Cache read $0.25Context 1,000,000Output limit 128,000
  • AI/ML APIGateway
    $2.12 / $6.35
    Cache read $0.26Context 1,000,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
DevPass (LLM Gateway)Gateway$2.00$6.00$0.25—1,000,0001,000,000
OpenRouterGateway$2.00$6.00$0.25—1,000,000128,000
LLM GatewayGateway$2.00$6.00$0.25—1,000,0001,000,000
Kilo GatewayGateway$2.00$6.00$0.25—1,000,000128,000
EmpirioLabs AIGateway$2.00$6.00$0.25—1,000,000131,072
Vercel AI GatewayCloud$2.00$6.00$0.25—1,000,0001,000,000
Merge GatewayGateway$2.00$6.00$0.25—1,000,000128,000
NanoGPTGateway$2.00$6.00$0.25—1,000,000128,000
AI/ML APIGateway$2.12$6.35$0.26—1,000,000128,000

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 = max

Your usage cost

Common scenarios
1DevPass (LLM Gateway)$490.00
2OpenRouter$490.00
3LLM Gateway$490.00
4Kilo Gateway$490.00
5EmpirioLabs AI$490.00
6Vercel AI Gateway$490.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $3.00

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-11). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

saFugu Ultra v2same series—saFugu Ultra v2.0same series—saFugu Ultra v1.1same series—saSakana Namazusame lab$0.95 / $4.00saFugu Ultrasame lab$5.00 / $30.00
Data partly from models.dev (MIT)