OpenInference — pricing & performance
Models served
3
of 1,109 tracked models
Mean output speed
29
tokens per second, averaged over
3 measured endpoints
3 measured endpoints
Mean latency
2.2s
time to first token, averaged over
3 measured endpoints
3 measured endpoints
Cheapest blended
$0.077
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on OpenInference
Output tokens per second for all 3 models on OpenInference 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 OpenInference
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | $0.070 | $0.18 | $0.098 | 7 | 4.9s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash 0731
|
DeepSeek | $0.050 | $0.16 | $0.077 | 29 | 1.2s | 1.05M |
Google: Gemma 4 31B
|
$0.070 | $0.35 | $0.14 | 50 | 0.4s | 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.