Working with LLM APIs · TRACK 02/05
Provider Guides
Hands-on first steps with every major door into the models.
// THE TRACK
01 · START HEREClaude APIGo from zero to your first successful Claude API call, understanding the Messages format, model lineup, and pricing along the way.BEGINNEROpenAI APIGo from zero to your first OpenAI API call, understanding model choices, the Chat Completions format, the newer Responses API, and how token billing works.BEGINNERBedrock & Vertex AILearn why enterprises call Claude through Bedrock or Gemini through Vertex, and what changes versus hitting the provider directly.INTERMEDIATEGemini APIGet a Gemini key from AI Studio and make your first call, with the free tier, long-context limits, and pricing demystified.BEGINNEROpenAI API for GPTMake your first GPT call and understand OpenAI's endpoints, model names, and billing before they confuse you.BEGINNEROpenAI-Compatible APIsUnderstand why so many providers and local servers speak 'OpenAI-compatible' and how changing one base_url lets the OpenAI SDK talk to a different model.INTERMEDIATEOpenRouterLearn how a model-aggregator endpoint lets you call hundreds of models through one key and one schema, and the tradeoffs versus going direct to each provider.BEGINNERLLM Gateway ProxyUnderstand the gateway pattern — a proxy between your services and LLM providers — and the key management, spend caps, logging, and routing it centralizes.INTERMEDIATE