Skip to main content

​
Enterprise & research AI coding models

Anthropic Claude AI

Claude 3.5 Sonnet LLM with advanced reasoning for AI code generation

OpenAI GPT models

GPT-4o and o1 series AI models for intelligent code completion

Google Gemini AI

Gemini 2.0 Flash LLM via GCP Vertex AI for AI-powered development

DeepSeek AI coding

DeepSeek V3 advanced reasoning models for cost-effective AI code generation

​
Fast LLM inference & specialized AI coding

Groq fast AI inference

Ultra-fast LPU inference for real-time AI code completion

Together AI models

50+ open-source LLMs for flexible AI code generation

Hyperbolic AI

Optimized open-source LLM inference for AI development

Perplexity AI search

AI coding with integrated web search for context-aware development

XAI Grok models

Grok LLMs with large context windows for AI code generation

Fireworks AI

Fast LLM inference with 40+ AI models for code generation

​
Open-source AI models & community LLMs

Cohere AI models

Command R series LLMs for AI code generation and development

HuggingFace AI hub

Thousands of open-source community AI models for code generation

Mistral AI coding

Mistral and Codestral LLMs specialized for AI-powered development

Moonshot AI

Kimi series LLMs with Chinese language support for AI coding

​
Unified & Routing

OpenRouter

Multiple models, unified API

OpenAI Compatible

Any OpenAI-compatible endpoint

​
Cloud & Enterprise

AWS Bedrock

Enterprise AI via AWS

GitHub Models

Models through GitHub platform

​
Local AI models & private LLM inference

Ollama local AI

Run open-source LLMs locally with Ollama for private AI code generation

LM Studio local models

Desktop app for running local AI models with private code generation

​
Choosing an AI coding provider

AI performance & speed:
  • Ultra-fast LLM inference: Groq, Together AI, Fireworks for real-time code completion
  • Best AI reasoning: Anthropic Claude, DeepSeek, OpenAI o1 for complex code generation
  • Balanced AI models: OpenAI GPT-4, Google Gemini, Cohere for general development
AI model cost:
  • Free/Low-cost AI: Local models (Ollama, LM Studio), OpenRouter for budget development
  • Budget-friendly LLMs: Together AI, HuggingFace, Hyperbolic for cost-effective coding
  • Premium AI models: Anthropic Claude, OpenAI GPT-4, Google Gemini for enterprise
AI privacy & security:
  • Maximum privacy: Local LLMs (Ollama, LM Studio) for private code generation
  • Enterprise-grade AI: AWS Bedrock, Anthropic for secure development
  • Cloud AI security: OpenAI, Google, Cohere with data protection
AI coding capabilities:
  • Code generation: All LLM providers, specialized: Cohere, Together AI for development
  • Multimodal AI: Google Gemini, OpenAI GPT-4 Vision, Moonshot for visual coding
  • Long context LLMs: Claude (200K+), Gemini (1M+), GPT-4 (128K) for large codebases
  • AI search integration: Perplexity for context-aware code generation
  • Multilingual AI: Cohere, Google, Moonshot (Chinese) for international development

​
Quick Start

1

Choose Provider

Select based on needs: speed, cost, capabilities, or privacy
2

Get Credentials

Sign up and get API keys (cloud) or install software (local)
3

Configure CodinIT

Add credentials in CodinIT settings
4

Select Model

Choose from available models
5

Start Building

Begin using AI in your workflow

​
Notes

  • Multi-provider: Configure multiple providers and switch between them
  • API security: Keys stored locally, never transmitted to CodinIT servers
  • Rate limits: Each provider has different limits
  • Local vs Cloud: Local offers privacy but requires hardware; cloud offers convenience and advanced features