kitio.aiAll AI tools
Every tool in the directory (10,042). Filter by category and price, or search by what you want to do.
Every tool in the directory (10,042). Filter by category and price, or search by what you want to do.
508 tools for “LLM Proxy”
Few tools use these exact words, so these also include tools that match what you mean.
Open-source gateway to call 100+ LLM providers in OpenAI format
Open-source LLM observability, prompt management and evals
Command-line tool and Python library for working with any LLM
AI gateway with observability, guardrails and prompt management
Flat monthly LLM API with unlimited tokens and request-based limits
Programming language for prompting LLMs with types and constraints
Cloud for running AI inference, agents and apps in production
The main hub for open models, datasets and AI demo apps
Anthropic's developer platform and API for building with Claude models
Developer API for GPT, reasoning, image, audio and embedding models
App platform with managed AI inference, agents and MCP
OpenAI models served from Microsoft Azure with enterprise controls
Serverless inference for open models on Cloudflare's global network
Developer API for Grok text, image, video and voice models
Tracing, evaluation and deployment platform for LLM agents
C/C++ engine for running LLMs efficiently on CPUs and GPUs
NVIDIA's optimized model containers and hosted API catalog
SDK that compiles and optimizes models for fast inference on NVIDIA GPUs
High-throughput open-source engine for serving LLMs in production
Experiment tracking and LLM observability, now part of CoreWeave
Pay-per-use AI support agent for web, WhatsApp, Telegram and LINE
FinOps layer that meters, caps and routes LLM and agent spend
Very fast inference API for open models on custom LPU chips
Specialized AI cloud for large-scale GPU training and inference
On-demand GPU pods and serverless endpoints for AI workloads
Run and deploy open-source AI models through a simple API
Fast inference and fine-tuning platform for open models
Serverless cloud for running Python and GPU workloads on demand
Wafer-scale chips serving open models at record inference speeds
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.