SSakana: Sakana Namazu
sakana/sakana-namazuSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts.
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.95 | $4.00 | $0.15 | 1.44s | 70 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Sakana Namazu in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Sakana Namazu costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider.
This measurement has not been published for the model yet. It appears as soon as it is.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run Sakana Namazu, by tokens this week.
Activity
149.0M tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.


