LLM Inference & Serving

Build with Gemini.

Bring Grok into your terminal.

Google's AI assistant

Enterprise technology platform

Generative media platform for developers.

Get up and running with large language models.

Meet your thinking partner

The AI community building the future.

One API for many models.

Develop with Claude

Run local language models on your computer.

A new beginning.

SubQ

Continual learning and adaptation after deployment.

AFM model playground

Production AI agents

The AI Gateway for developers

One API for 1000+ AI models

Build and scale generative AI applications with foundation models.

Enterprise AI platform for language models

A Unified, Open Source RL Backend for Enterprise Post-Training

A SuperPoD AI infrastructure option for large-scale AI training and inference.

Run local AI models on your device

LLM API for Baidu AI Studio

An enterprise-grade, all-in-one large model platform centered on Agent development

AI inference platform

Hosted AI inference and API service

Manage every agent and provider from one place.

Claude on AWS

Best Subscription for Open Weight Models.

Build full-stack AI applications on Cloudflare

Comprehensive LLM serving solution for Huawei CloudMatrix384

Coding Agents

Software product by Conway Research

Bring PyTorch models to Core AI for on-device execution.

Platform for Accelerated Computing

Data and AI for all

Ship AI that keeps getting better.

Claude-powered reasoning and chat

Efficient expert-parallel communication library

Clean and efficient FP8 GEMM kernels with fine-grained scaling.

Block Diffusion for Flash Speculative Decoding

Personal AI platform from NVIDIA

State-of-the-art pretrained diffusion models

Model architecture summarizer for AI/ML model files

Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Software product by antirez

Run frontier AI locally.

Automatically select the best model for each task.

FIne tuning with NO labels

Fast, scalable infrastructure for generative AI.

Bringing Flash Magic to Classical Machine Learning Operators

Efficient MLA decoding kernel for Hopper GPUs

High-throughput tensor loading for PyTorch -- load models at up to 25Gbps without GDS.

FlashQLA

An LLM Pretraining Framework Built End-to-End by an Autonomous Agent Loop

Pure-Rust, CPU-only OCR engine with a five-model zoo and no Python, CUDA, ML framework, or GPU required at inference.

Real-time multimodal API for Gemini.

AI Coding Powered by GLM-5.2 & GLM-5-Turbo for Agents & IDEs

Explore and run AI models on-device.

Run local LLMs on your own hardware.

Fast AI inference platform

Unverified product associated with Garry Tan.

SLO-aware Benchmarking and Evaluation Platform for Optimizing Real-World LLM Inference

The platform for scalable, reliable, and efficient inference

AI-assisted interface builder

The Universal Gateway for AI Inference

Control every model call

Build, train, and deploy AI apps.

OpenAI-compatible API for all LLMs

LLM inference in C/C++

llmster

Product details unavailable

Supercharge Your LLM with the Fastest KV Cache Layer

Build with Muse Spark on Meta Model API - now in public preview for US developers.

Enterprise-Grade Reinforcement Learning for Large-Scale Model Training

Augment your apps with AI

Your AI production platform.

AI software product

Model-as-a-Service

Inference reimagined, from Kernel to Cloud. One unified stack.

A KVCache-centric Disaggregated Architecture for LLM Serving.

Inference Built for Coding Agents

Multimodal AI software product

Software product named Naïve

A scalable and efficient post-training library

Next-Generation LLM Gateway and AI Asset Management System

Everything to power your Hermes Agent

Runtime for AI agents to execute real-world tasks

The foundation for your AI factory.

NVIDIA NIM microservices

4-bit floating-point format and low-precision recipe for efficient AI training and inference.

Free AI Image & Video Studio

AllenAI's post-training codebase

Open-source specification and ecosystem for multi-provider, interoperable LLM interfaces.

Guaranteed access to OpenAI capacity

Build leading AI products on OpenAI’s platform

OpenMythos

2-10x accuracy improvements on reasoning tasks with zero training

One AI gateway: adaptive LLM routing & governance

AI Toolkit

One-stop AI teaching and training platform

C++ software project

Software product by Fastino Inc.

Machine Learning Platform for AI

A TTS that fits in your CPU (and pocket)

Decentralized AI platform

Prime Intellect Lab

PrismML platform

Define functions in English. Run them locally.

Tile primitives for speedy kernels

Serving LLMs

DeepSeek-native coding agent for your terminal

Advancing biological preparedness with trusted developers and government partners.

The AI Developer Cloud

High-performance serving framework for large language and multimodal models.

Ship reduces your LLM bill 50% without changing model behavior. Guaranteed by an SLA.

Edge AI platform

Open Medical Superintelligence

Official details could not be verified from source access in this run.

StepFun software product

Amortized KV Cache Compaction in a Single Forward Pass

Official Subquadratic product

Carrier-owned global communications platform for voice AI agents, SIP trunking, programmable voice, SMS/MMS, and AI inference.

AI Math, Re-Engineered. AI Inference, Re-Defined.

Compute for every scale.

Thinking Machines software platform

Optimized GPU kernels for LLM operations, built with TileLang.

A concise domain-specific language designed to streamline the development of high-performance GPU/CPU kernels.

Ascend TileLang adapter

AI development platform for open models

Fine-tune open-source models for real production use

Train Dreambooth models. Generate unlimited AI assets.

Fast LLM fine-tuning

Unsloth Studio

GPU cloud marketplace for renting and hosting GPU compute

Private, unrestricted access to all the leading AI models across text, image, video, and audio, behind one API key.

Build, deploy, and scale AI applications with Vertex AI.

Easy, fast, and cheap LLM serving for everyone

Production inference for encoders, poolers, and structured prediction — as vLLM plugins.

Easy, fast, and cheap omni-modality model serving for everyone

The fastest inference on any silicon

Workers AI provider for the AI SDK.

Unified API for all models, intelligent routing, and AI Model Insurance.

AI cloud from Zyphra

Inference for Zyphra models

一站式大模型开发及应用构建平台