Educational Purpose Only - Legal Disclaimer

This tool is provided strictly for educational and research purposes. By using this information, you acknowledge responsibility for compliance with all applicable terms of service, licenses, and laws.

Reference

Compatible API Providers

Popular OpenAI-compatible API providers you can use with Claude Code CLI

OpenAIPopular
https://api.openai.com/v1

Official OpenAI API with GPT-4, GPT-4 Turbo, and GPT-4o models

Models

gpt-4ogpt-4o-mini+2

Features

Tool UseVisionJSON Mode
OpenRouterPopular
https://openrouter.ai/api/v1

Access multiple AI providers through a single API, including Claude, GPT-4, Llama, and more

Models

anthropic/claude-3.5...openai/gpt-4o+1

Features

Multi-ProviderFallbacksCost Optimization
Together AI
https://api.together.xyz/v1

Fast inference for open-source models with competitive pricing

Models

meta-llama/Llama-3.1...mistralai/Mixtral-8x...

Features

Open SourceFast InferenceFine-tuning
GroqPopular
https://api.groq.com/openai/v1

Ultra-fast inference with LPU technology for supported models

Models

llama-3.1-70b-versat...llama-3.1-8b-instant+1

Features

Ultra FastFree TierLow Latency
Fireworks AI
https://api.fireworks.ai/inference/v1

Optimized inference for open-source and custom models

Models

accounts/fireworks/m...accounts/fireworks/m...

Features

FastCustom ModelsFunction Calling
Ollama
http://localhost:11434/v1

Run models locally on your machine with complete privacy

Models

llama3.1codellama+2

Features

LocalPrivateNo API Key
LM Studio
http://localhost:1234/v1

Local inference with a user-friendly GUI for model management

Models

Various GGUF models

Features

LocalGUINo API Key
vLLM
http://localhost:8000/v1

High-throughput inference server for self-hosted deployments

Models

Self-hosted models

Features

Self-HostedHigh ThroughputPaged Attention

Privacy Note

When using local providers like Ollama or LM Studio, all inference happens on your machine. Your code and conversations never leave your device. For cloud providers, review their privacy policies and data retention practices.

OpenAI-Compatible API Providers

Many AI providers offer OpenAI-compatible APIs, allowing you to use Claude Code CLI with various models and services. Here's an overview of popular options:

Cloud Providers

  • OpenRouter: Unified API for 100+ models including Claude, GPT-4, and open-source models
  • Groq: Ultra-fast inference with Llama and Mixtral models on custom LPU hardware
  • Together AI: Wide selection of open-source models with competitive pricing
  • Fireworks AI: Fast inference optimized for production workloads
  • Deep Infra: Serverless inference for popular open-source models

Local Options

  • Ollama: Run LLMs locally on your machine with easy model management
  • LM Studio: Desktop app for running local LLMs with a GUI interface

Choosing a Provider

Consider factors like model availability, pricing, speed, and whether you need local or cloud-based inference. OpenRouter is often recommended for its wide model selection and unified billing.