Skip to content
Sovyron

Sakana Namazu

sakana-namazu262k context262k max outputreleased Aug 3, 2026ReasoningTool calling

As of Nov 22, 2026, the cheapest Sakana Namazu API price is $0.95 per 1M input tokens (Kilo Gateway) and $4 per 1M output tokens (Kilo Gateway). Sakana Namazu is offered by 7 providers in the sakana-namazu family, reasoning enabled.

Cheapest input
$0.95
Cheapest output
$4
Official
—
output per 1M tokens
Providers
7
offering this model
Spread
1.0×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

Sakana Namazu API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Kilo Gatewaysakana/sakana-namazuCheapest$0.95Cheapest$4$0.15—262k
DevPass (LLM Gateway)sakana-namazu$0.95$4$0.15—262k
LLM Gatewaysakana/sakana-namazu$0.95$4$0.15—262k
Merge Gatewaysakana/sakana-namazu$0.95$4$0.15—262k
OpenRoutersakana/sakana-namazu$0.95$4$0.15—262k
Sakana AIsakana-namazu$0.95$4$0.15—262k
Vercel AI Gatewaysakana/namazu$0.95$4$0.15—256k

Sakana Namazu pricing FAQ

What is the cheapest Sakana Namazu API?

As of Nov 22, 2026, Kilo Gateway has the lowest Sakana Namazu output price at $4 per 1M tokens, and Kilo Gateway has the lowest input price at $0.95 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Sakana Namazu?

7 providers list Sakana Namazu on Sovyron; 7 of them sell it at a metered per-token price.

Is Sakana Namazu free?

No provider in the Sovyron catalog lists a free tier for Sakana Namazu.

What is the context window of Sakana Namazu?

Sakana Namazu supports a 262k-token context window and up to 262k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—