Modeldex
Sakana

Sakana Namazu

CTX262K
Reasoning · Vision · Tools
TextImagePDFInput$0.95/M
TextOutput$4/M

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

PaidProprietary963/1044
Drag to turnCard front showing

SakanaTextUncommon

Sakana Namazu

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

sakana-namazu
Type
Text
Quality
Not rated yet
Context window
262,144 tokens
Max output
65,536 tokens
Input price
$0.95 / 1M tokens
Output price
$4.00 / 1M tokens
Cache read
$0.15 / 1M tokens
Cache write
—
Released
Aug 3, 2026
Knowledge cutoff
—
Takes in
Text, Image, PDF
Puts out
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
File attachments
Yes
Access
Paid
License
Proprietary
Rarity
Uncommon
Set number
963/1044

Weights aren’t public. Use is governed by Sakana’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: console.sakana.ai.

How good is it?

Public leaderboard scores for Sakana Namazu, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Sakana Namazu yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

5 providers sell Sakana Namazu through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
Kilo GatewayCheapest paidsakana/sakana-namazu$0.95$4.00262K
Merge Gatewaysakana/sakana-namazu$0.95$4.00262K
OpenRoutersakana/sakana-namazu$0.95$4.00262K
Sakana AIOfficialsakana-namazu$0.95$4.00262K
Vercel AI Gatewaysakana/namazu$0.95$4.00256K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

More from Sakana

Sakana

Fugu Ultra

CTX1M
Reasoning · Vision · Tools
TextImageInput$5/M
TextOutput$30/M

Quality-first multi-agent model for hard research, analysis, and competitions

PaidProprietary927/1044
Sakana

Fugu

CTX1M
Reasoning · Vision · Tools
TextImageInput—
TextOutput—

Multi-agent model for routing expert agents across complex analytical tasks

PaidProprietary926/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot