OpenInference — pricing & performance
Models served
1
of 947 tracked models
Mean output speed
15
tokens per second, averaged over
1 measured endpoints
1 measured endpoints
Mean latency
3.1s
time to first token, averaged over
1 measured endpoints
1 measured endpoints
Cheapest blended
$0.16
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on OpenInference
Median output tokens per second for all 1 model on OpenInference with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 1 of 1 models⇩
The Known Good
1 model on OpenInference
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Google: Gemma 4 31B
|
$0.10 | $0.35 | $0.16 | 15 | 3.1s | 262k |
The Known Good
Source. Prices, endpoint availability and throughput for OpenInference 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.