Requesty documentation home page
Search...
⌘K
Get Started
Getting started
Models
Features
Streaming
Structured Outputs
Reasoning
Fallback Policies
Load Balancing
Set API Limits
Key Management API
Auto Caching
Dedicated Models
Prompt Optimization
Prompt Library
Bring Your Own Keys
Request Metadata
Request Feedback
Smart Routing
Session Reconstruction
Applications
Cline
LibreChat
Roo Code
OpenWebUI
VS Code Extension
Frameworks
Axios
Requests
OpenAI
LangChain
LlamaIndex TS
Haystack
PydanticAI
Vercel AI SDK
API Reference
Overview
POST
Create Chat Completion
GET
Get API Keys
POST
Create API Key
GET
Get API Key Usage
POST
Update API Key Limit
DEL
Delete API Key
GET
Get Organization Info
Join us on Discord
Go to the Platform
Requesty documentation home page
Search...
⌘K
Join us on Discord
Go to the Platform
Go to the Platform
Search...
Navigation
Features
Dedicated Models
Features
Dedicated Models
Application-specific models
Some of our models are optimized for specific applications. Those models require the application name to be added instead of the provider.
Coding
We created a coding optimized model, which enables:
Auto caching of your prompts when using Anthropic and Gemini
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:
Copy
coding
/
claude
-
3
-
7
-
sonnet
You can find all the latest Coding models in the
Model Library
.
Previous
Prompt Optimization
Customize and optimize your system prompts
Next
On this page
Coding
Assistant
Responses are generated using AI and may contain mistakes.