Skip to main content
Some of our models are optimized for specific applications. Those models require the application name to be added instead of the provider.
Browse dedicated models in the Requesty Console.

​
Coding

We created a coding optimized model, which enables:
  1. Auto caching of your prompts on providers that support prompt caching
  2. Handles compatibility when interacting with reasoning OpenAI’s and Deepseek’s reasoning models
You can use those models by adding coding as the provider in front of the model name, like this: coding/<MODEL_NAME>. For example:
You can find all the latest Coding models in the Model Library.
Last modified on August 16, 2026