PrimaLabs — pricing & performance
Models served
3
of 1,293 tracked models
Mean output speed
151
tokens per second, averaged over
3 measured endpoints
3 measured endpoints
Mean latency
0.8s
time to first token, averaged over
3 measured endpoints
3 measured endpoints
Cheapest blended
$0.42
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on PrimaLabs
Output tokens per second for all 3 models on PrimaLabs with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 3 of 3 models⇩
The Known Good
3 models on PrimaLabs
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
|
|
DeepSeek | $0.24 | $0.96 | $0.42 | 170 | 0.4s | 1.05M |
|
|
Moonshot AI | $2.70 | $13.50 | $5.40 | 89 | 1.2s | 1.05M |
| Mi Xiaomi: MiMo-V2.6-Pro | Xiaomi | $4.00 | $8.00 | $5.00 | 195 | 0.7s | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for PrimaLabs 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.