.pricing
Inference pricing
Our Large Language Models for Chat and Completions are available via BRAHMAI Inference API. For these models you pay just for what you use.
Serverless Endpoints
Prices are per 1 million tokens including input and output tokens for Chat, Language and Code
models.
-
Chat, language, and code models
-
Model Name
price 1M tokens
-
Cerberus
price 1M tokens
$0.75
-
Cerberus Lite
price 1M tokens
$1.5
-
Garud
price 1M tokens
$18.75
-
Garud Lite
price 1M tokens
$10
-
-
DEDICATED COMPLETIONS ENDPOINT MODELS
-
Model Name
price hour
-
lil-c3po v1
price 1M tokens
$0.50
-
lil-c3po v2
price 1M tokens
$0.75
-
Tiny Cerberus
price 1M tokens
$2.40
-
-
DEDICATED DEPLOYMENTS
Providing dedicated deployments is more complex. It requires strategic resource allocation to meet the requirements. Please contact us at hello@brahmai.in for any queries or fill out this form.
Interested in a on-premesis deployments?