LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
sa

Sakana Namazu

sakana·sakana/sakana-namazu·GA·Closed·sakana-namazu series
Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

Specs & pricing

Input / output per 1M tokens
Official price·Sakana AI
$0.95 / $4.00
Blended $1.71 · Cache read $0.15
Lowest paid·Sakana AIFirst-party
$0.95 / $4.00
Blended $1.71 · 1× spread
Context
262,144
Output limit
65,536
Knowledge cutoff
—
Released / updated
2026-08-03 / 2026-08-03
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF
References
Official product pageOfficial model documentation

Sakana Namazu is offered by 7 providers on this page. Its official list price is $0.95 per 1M input tokens and $4.00 per 1M output tokens. No paid channel is priced below the official list price.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 256,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF.

Available at 7 providers7 with public prices

  • ProviderInput / Output
  • Sakana AIOfficialFirst-party
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 65,536
  • LLM GatewayGateway
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 262,144
  • DevPass (LLM Gateway)Gateway
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 65,536
  • Merge GatewayGateway
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 65,536
  • OpenRouterGateway
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 65,536
  • Kilo GatewayGateway
    $0.95 / $4.00
    Cache read $0.15Context 262,144Output limit 65,536
  • Vercel AI GatewayCloud
    sakana/namazu
    $0.95 / $4.00
    Cache read $0.15Context 256,000 ⚠Output limit 256,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Sakana AIOfficialFirst-party$0.95$4.00$0.15—262,14465,536
LLM GatewayGateway$0.95$4.00$0.15—262,144262,144
DevPass (LLM Gateway)Gateway$0.95$4.00$0.15—262,14465,536
Merge GatewayGateway$0.95$4.00$0.15—262,14465,536
OpenRouterGateway$0.95$4.00$0.15—262,14465,536
Kilo GatewayGateway$0.95$4.00$0.15—262,14465,536
Vercel AI Gateway
sakana/namazu
Cloud$0.95$4.00$0.15—256,000 ⚠256,000

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

Toggle (on / off)effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max

1 / 7 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Sakana AI · Official$294.00
2LLM Gateway$294.00
3DevPass (LLM Gateway)$294.00
4Merge Gateway$294.00
5OpenRouter$294.00
6Kilo Gateway$294.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.00$02026-08-112026-08-18
2026-08-18Input list $0.95Output list $4.00Min blended $1.71

Benchmark6 items

NameConditionsScoreMetricSource
AIME26—96.67—Source ↗
MMLU-Pro—90.33—Source ↗
LiveCodeBench v6—90.33—Source ↗
JFBench—37.4—Source ↗
Translation—52.2—Source ↗
FairPoliticsQA—56.3—Source ↗

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

Related models

GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20saFugu Ultra v2same lab—saFugu Maxsame lab—
Data partly from models.dev (MIT) · Sakana AI official docs ↗