LLM APIs & Model Providers
Model APIs, inference platforms and gateways for building with large language models. 90 tools listed. See also the guide to the best LLM APIs & Model Providers tools.
Your tool could be here
Featured spots are labeled "Sponsored" and sit at the top of the directory and your category.
Get featured →-
AI/ML API
Single API giving access to hundreds of AI models.
-
AI21 Labs
AI lab offering the Jamba models and enterprise AI tools.
-
Alibaba Cloud Model Studio
Alibaba Cloud's platform for accessing and building on Qwen and other models.
-
Amazon Bedrock
AWS service offering foundation models from multiple providers through one API.
-
Anthropic API
Anthropic's developer API for the Claude family of models.
-
Anyscale
Managed platform for running Ray-based AI workloads.
-
Arcee AI
U.S. lab building open-weight language models, available to download or through an API.
-
Azure AI Foundry
Microsoft's platform for building and managing AI apps and agents with a catalog of models.
-
Baseten
Inference platform for deploying and serving AI models.
-
Beam
Serverless GPU platform for running AI inference, sandboxes and background jobs in Python.
-
Caveman
Cuts AI coding-agent token costs with recoverable context compression and usage tracking.
-
Cerebras
AI hardware company offering high-speed inference for open models.
-
Chutes
Decentralized serverless inference platform for running open-source AI models.
-
Cloudflare AI Gateway
Gateway for caching, rate limiting and observing AI API traffic.
-
Cloudflare Workers AI
Run AI models on Cloudflare's network via serverless APIs.
-
Cohere
Enterprise AI company offering language models, embeddings and rerank APIs.
-
Conifer
LLM gateway and router that picks a model for each request, built for government and enterprise.
-
CoreWeave
GPU cloud provider for training and running large AI models.
-
Crusoe
AI cloud provider offering GPU compute and managed inference.
-
Databricks Mosaic AI
Databricks' tools for building, serving and governing AI models and agents.
-
DeepInfra
Hosted inference for open-source models via API.
-
DeepSeek API
Developer documentation for the DeepSeek model API.
-
Eden AI
Unified API for many AI providers covering LLMs, speech, vision, translation and document parsing.
-
ExLlamaV2
Open-source inference library for running LLMs on consumer GPUs.
-
fal
Generative media platform with API access to image, video and audio models plus serverless GPUs.
-
Featherless
Serverless inference for a large catalog of open models on Hugging Face.
-
Fireworks AI
Inference platform for open and fine-tuned generative models.
-
Fluidstack
AI cloud provider of large GPU clusters for training and inference.
-
FriendliAI
Inference platform for serving open and custom generative models.
-
Google AI Studio
Google's web tool and API gateway for prototyping with Gemini models.
-
Groq
Fast inference platform that runs open models on custom LPU hardware.
-
Hugging Face
Hub for open models, datasets and apps, with hosted inference.
-
Hyperbolic
GPU cloud and inference API for open models, with on-demand GPU rentals.
-
Hyperstack
GPU cloud for AI training and inference with NVIDIA GPUs.
-
IBM watsonx.ai
IBM's studio for building, tuning and deploying foundation models and AI applications.
-
Inception
Builds Mercury, a family of diffusion-based language models, offered through an API.
-
Inference.net
Inference platform for running and fine-tuning open models, with batch and real-time APIs.
-
Infermatic
Hosted inference API for open-source language models.
-
Jarvislabs
GPU cloud for AI training and fine-tuning with on-demand instances.
-
Kimi API Platform
Developer API platform for Moonshot AI's Kimi large language models.
-
Kong AI Gateway
AI gateway for governing and securing LLM and MCP traffic.
-
Lambda
GPU cloud offering on-demand instances and reserved clusters for training and running AI models.
-
Lepton AI
Serverless GPU inference and model deployment platform.
-
Lightning AI
Cloud platform for building, training and serving AI models, from the PyTorch Lightning team.
-
Liquid AI
AI company building efficient foundation models (LFMs) designed to run on devices and in the cloud.
-
LiteLLM
Open-source gateway for calling many LLM providers through one OpenAI-style interface.
-
Llama
Meta's family of open-weight models with downloads and developer resources.
-
Llamafile
Mozilla project that packages LLMs into single-file executables.
-
LocalAI
Open-source, OpenAI-compatible API for running models locally.
-
Martian
Model routing that picks among LLMs for each request.
-
MiniMax
AI company offering text, speech, video and music models through its own apps and a developer API platform.
-
MLC LLM
Universal LLM deployment engine for running models on many devices.
-
Modal
Serverless cloud for running AI workloads and model inference.
-
Modular MAX
Inference and serving stack from Modular for running AI models.
-
Munito AI
European LLM inference API for open models, private by default.
-
Nebius
AI cloud with GPU infrastructure and managed inference.
-
Not Diamond
Model router that picks the best-suited LLM for each request, plus prompt optimization.
-
Nous Research
Open AI research lab behind the open-weight Hermes models and Hermes Agent.
-
Novita AI
Cloud platform offering model APIs and GPU instances.
-
Nscale
AI hyperscaler offering GPU compute and serverless inference for model training and deployment.
-
NVIDIA NIM
NVIDIA's catalog of model endpoints and microservices for inference.
-
OpenAI API
OpenAI's developer platform for its language, image, audio and agent APIs.
-
OpenRelay
AI inference at a flat monthly rate for reserved throughput, plus hourly GPU VMs.
-
OpenRouter
Unified API that routes requests to many model providers.
-
OVHcloud AI Endpoints
Serverless API access to open-source AI models from OVHcloud.
-
Parasail
GPU inference network for running open models through serverless or dedicated endpoints.
-
Perplexity API
Perplexity's API for search-grounded answers.
-
Portkey
AI gateway for routing, observing and governing LLM requests.
-
Reka
AI lab offering multimodal models and APIs.
-
Replicate
Run and deploy machine learning models through a simple API.
-
Requesty
LLM gateway and router that gives one API for many model providers with fallbacks and cost controls.
-
RouterPlus
LLM inference and routing that picks models based on your own evals and production traffic, behind one API key.
-
Runware
Image and video generation inference API for many models.
-
Sakana AI
Tokyo AI lab building efficient foundation models and multi-model orchestration systems.
-
SaladCloud
Distributed GPU cloud that runs AI inference on a network of consumer GPUs.
-
SambaNova
AI infrastructure and inference cloud for open and custom models.
-
Sarvam AI
Indian AI company offering language, speech and translation models for Indian languages through an API.
-
Scaleway Generative APIs
European serverless API for open-weight LLMs hosted by Scaleway.
-
Segmind
Serverless API platform for image, video and other generative models, with a workflow builder.
-
SiliconFlow
Inference cloud offering APIs for many open-source language, image and video models.
-
TensorDock
Marketplace for renting cloud GPUs for AI and rendering.
-
TensorRT-LLM
NVIDIA open library for high-performance large language model inference.
-
Together AI
Cloud for running, fine-tuning and deploying open-source models.
-
Upstage
AI company offering Solar language models and document AI APIs.
-
Vast.ai
Marketplace for renting GPUs from many providers by the hour.
-
Vercel AI Gateway
Vercel's gateway giving one endpoint for many AI model providers, with usage tracking and fallbacks.
-
Vertex AI
Google Cloud's platform for building and deploying generative AI and ML models.
-
Vultr
Cloud provider with cloud GPUs and serverless inference for AI workloads.
-
WaveSpeedAI
Inference API for fast image and video generation models.
-
xAI API
xAI's developer API for its Grok language, image and voice models, billed by usage.