OpenInference — pricing & performance
Models served
4
of 1,128 tracked models
Mean output speed
22
tokens per second, averaged over
4 measured endpoints
4 measured endpoints
Mean latency
3.3s
time to first token, averaged over
4 measured endpoints
4 measured endpoints
Cheapest blended
$0.055
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on OpenInference
Output tokens per second for all 4 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 4 of 4 models⇩
The Known Good
4 models on OpenInference
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | $0.050 | $0.14 | $0.072 | 18 | 1.5s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash 0731
|
DeepSeek | $0.040 | $0.10 | $0.055 | 18 | 1.9s | 1.05M |
Google: Gemma 4 31B
|
$0.070 | $0.35 | $0.14 | 50 | 0.4s | 262k | |
Z.ai: GLM 5.3 Flash
|
Z.ai | $0.15 | $0.50 | $0.24 | 1 | 9.5s | 1.05M |
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.