o1-mini
Neural Network
GPT o1 mini is a flexible and fast neural network specifically designed for mathematical and coding tasks. It works excellently in resource-constrained environments, speeding up data analysis and process automation. Thanks to its ability to promptly handle queries, the model is suitable for mobile applications and systems where low latency is crucial.
65 536
Max. Response Length
(in tokens)
128 000
Context Size
(in tokens)
1,1 USD
Prompt Cost
(per 1M tokens)
4,4 USD
Response Cost
(per 1M tokens)

BotHub: Try for freebot