InferenceNet — pricing & performance
Models served
2
of 1,122 tracked models
Mean output speed
62
tokens per second, averaged over
2 measured endpoints
2 measured endpoints
Mean latency
1.7s
time to first token, averaged over
2 measured endpoints
2 measured endpoints
Cheapest blended
$0.060
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on InferenceNet
Output tokens per second for all 2 models on InferenceNet with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 2 of 2 models⇩
The Known Good
2 models on InferenceNet
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
| IN Inference.net: Schematron V2 Small | inference-net | $0.050 | $0.23 | $0.095 | 98 | 0.9s | 128k |
| IN Inference.net: Schematron V2 Turbo | inference-net | $0.030 | $0.15 | $0.060 | 26 | 2.5s | 128k |
The Known Good
Source. Prices, endpoint availability and throughput for InferenceNet 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.