API

Concept

LLM Cost Optimization

The operational playbook for cutting LLM spend without cutting quality. Model routing, caching, batching, and the metrics that actually matter.

Tool Guide

LiteLLM Guide

The definitive guide to LiteLLM for multi-model routing — OpenAI-compatible proxy, fallbacks, cost tracking, and self-host setup for production AI apps.

Workflow

Build an MCP Server from Your API

Wrap your REST or GraphQL API as an MCP server so Claude Desktop, Cursor, and any MCP client can call it — write once, use everywhere.

Comparison

Cheapest AI APIs

Per-million-token cost comparison across providers, with notes on where the cheap models are actually good enough.

Comparison

Local Models vs API Models

Should you run LLMs on your own hardware or pay OpenAI and Anthropic? An honest comparison on privacy, cost, latency, quality, and the ops burden nobody talks about upfront.

Directory

01.AI

Kai-Fu Lee's Chinese AI company behind the Yi family of open bilingual models and enterprise-focused LLM solutions.

Directory

AI21 Labs

Israeli AI lab behind the Jamba hybrid SSM-Transformer open models and Maestro, a system for reliable agent orchestration.

Directory

Aleph Alpha

German sovereign AI company offering the PhariaAI stack with explainability features for regulated industries and government.

Directory

Anthropic API

Anthropic's developer API for the Claude model family, with tool use, prompt caching, batching, and long-context support.

Directory

Baichuan AI

Beijing LLM developer offering the Baichuan model family, spanning open-weight releases and commercial APIs and assistants.

Directory

Cerebras Inference

Cloud API serving open models at very high token throughput on Cerebras wafer-scale chips.

Directory

Cohere

Enterprise AI platform offering Command, Embed, and Rerank models via API, focused on RAG and multilingual retrieval.

Directory

DeepInfra

Pay-per-token hosting for open-source models with an OpenAI-compatible API and dedicated GPU options.

Directory

ELYZA

University of Tokyo spinout building high-performing Japanese LLMs, including the open ELYZA Japanese Llama model series.

Directory

Exa

Semantic web search API. Find niche papers, blogs, and primary sources by meaning, not just keyword.

Directory

Fal

Fast inference platform for image, video, and audio models. Sub-second latency on diffusion workflows.

Directory

Fireworks AI

Inference platform serving open models with low latency, plus fine-tuning and compound AI system tooling.

Directory

FriendliAI

Korean inference platform serving open and custom LLMs with high-throughput GPU optimization via its Friendli Engine.

Directory

Google AI Studio

Google's free web-based developer environment for prototyping with Gemini models and generating Gemini API keys.

Directory

Groq

LPU-accelerated inference for open-weights LLMs. Hundreds of tokens per second; the speed leader.

Directory

Hugging Face

Community hub hosting over a million models, datasets, and Spaces, with open-source libraries and paid inference endpoints.

Directory

Instructor

Python library for structured LLM outputs — Pydantic models in, validated JSON out, with retries and provider switching.

Directory

Jina AI

Berlin-based search foundation company with embeddings, rerankers, and the Reader API for grounding LLMs in web content.

Directory

LightOn

French enterprise AI company offering Paradigm, an on-premise generative AI platform for private LLM deployment.

Directory

LiteLLM

Unified OpenAI-compatible proxy for 100+ LLM providers — routing, fallbacks, cost tracking, and key management in one gateway.

Directory

Maritaca AI

Brazilian lab founded by Unicamp researchers building Sabia, Portuguese-specialized LLMs available via chat and API.

Directory

Mistral AI

French AI lab offering open-weight and commercial models through the La Plateforme API and the Le Chat assistant.

Directory

Nebius

Amsterdam-headquartered AI cloud offering GPU clusters and Nebius AI Studio for open-model inference and fine-tuning.

Directory

OpenAI Platform

OpenAI's developer platform with APIs for GPT models, embeddings, images, speech, and agent tooling.

Directory

OpenRouter

Unified API gateway providing access to hundreds of models from many labs through one OpenAI-compatible endpoint.

Directory

Replicate

Hosted API for thousands of open-source models — image, video, audio, language.

Directory

SambaNova Cloud

AI chip company offering fast inference of open-source models on its RDU hardware through SambaNova Cloud.

Directory

Sarvam AI

Indian AI lab building Sarvam-M and other Indic-focused LLMs, with APIs for speech, translation, and text in Indian languages.

Directory

SenseTime

Chinese AI major offering the SenseNova foundation model family alongside its established computer vision platforms.

Directory

StepFun

Shanghai model lab building the Step series of multimodal foundation models spanning text, audio, image, and video.

Directory

Tavily

Search API engineered for LLM agents — clean snippets, structured results, no junk.

Directory

Together AI

Cloud platform for running, fine-tuning, and training open-source models on fast dedicated inference infrastructure.

Directory

Upstage

Korean AI startup behind the compact Solar LLM family and a Document AI stack for parsing, OCR, and information extraction.

Directory

xAI API

xAI's developer API for the Grok model family, including reasoning models and live search integration.