The Known Good Updated 14 Nov 2026 Subscribe
Providers· Inference host· 3 tracked models

PrimaLabs — pricing & performance

Compare models All providers Data sources
Models served
3
of 1,293 tracked models
Mean output speed
151
tokens per second, averaged over
3 measured endpoints
Mean latency
0.8s
time to first token, averaged over
3 measured endpoints
Cheapest blended
$0.42
per 1M tokens at a 3:1
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: DeepSeek V4.1 Flash 1017 DeepSeek $0.24 $0.96 $0.42 170 0.4s 1.05M
MoonshotAI: Kimi K3.1 Pro Moonshot AI $2.70 $13.50 $5.40 89 1.2s 1.05M
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.