5 docs tagged with "apis"

REST calls, authentication, and request/response anatomy for LLM APIs.

Python SDK setup, messages API, and streaming responses for OpenAI and Anthropic.

Ollama, vLLM, hardware requirements, and quantization (Q4/Q8) for self-hosting.

Token counting, cost estimation, batching, and caching strategies for LLM APIs.

Rate limits, timeouts, exponential backoff, and fallback model strategies.