Sakana AI — pricing & performance
Models served
4
of 1,128 tracked models
Mean output speed
42
tokens per second, averaged over
4 measured endpoints
4 measured endpoints
Mean latency
13.4s
time to first token, averaged over
4 measured endpoints
4 measured endpoints
Cheapest blended
$1.71
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Sakana AI
Output tokens per second for all 4 models on Sakana AI with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 4 of 4 models⇩
The Known Good
4 models on Sakana AI
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
| Sa Sakana: Fugu Max | sakana | $2.00 | $6.00 | $3.00 | 70 | 3.1s | 1.00M |
| Sa Sakana: Fugu Ultra | sakana | $5.00 | $30.00 | $11.25 | 8 | 8.2s | 1.00M |
| Sa Sakana: Fugu Ultra v2 | sakana | $5.00 | $30.00 | $11.25 | 52 | 41.3s | 1.00M |
| Sa Sakana: Sakana Namazu | sakana | $0.95 | $4.00 | $1.71 | 37 | 1.0s | 262k |
The Known Good
Source. Prices, endpoint availability and throughput for Sakana AI are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.