IN

Inference.net

Inference.net is an AI model provider.Tokenando tracks 2 Inference.net models, with input pricing from $0.0300/M and an average blended cost of $0.0850/M. Its flagship model is Inference.net: Schematron V2 Turbo.

Inference.net models reach Tokenando via OpenRouter. We do not yet have a curated profile for this provider, the model catalogue below comes straight from the OpenRouter snapshot and the live price feed.

ModelsUSD per million tokens. Blend is 70% input, 30% output, our calculation.

MODELS TRACKED
2
1 category
FLAGSHIP
Inference.net: Schematron V2 Turbo
text->text
MIN INPUT
$0.0300/M
cheapest model in family
AVG BLENDED
$0.0850/M
across 2 priced models
MAX CONTEXT
128,000
largest window in family

Frequently Asked Questions

How many models does Inference.net offer?

Tokenando tracks 2 Inference.net models.

How much do Inference.net models cost?

Inference.net model input pricing starts at $0.0300 per million tokens, with an average blended cost of $0.0850 per million across the 2 priced models we track.

What is Inference.net's flagship model?

Inference.net's flagship model is Inference.net: Schematron V2 Turbo. It is the highest-tier Inference.net model we track, with input pricing of $0.0300 per million tokens.

What model categories does Inference.net cover?

Inference.net covers 1 category: efficient.

Terms used on this page