AI Providers

Fast inference on LPU hardware. Best-in-class throughput for open-weight models including Llama and Mistral.

Affordable GPU cloud for open AI models. Serverless and dedicated instances.

GPU cloud with extremely low pricing for open AI models.

Optimized inference containers for NVIDIA GPUs. Enterprise-grade performance.

Edge AI inference via Cloudflare's global network. Low latency worldwide.

Gemini models via Google's AI Studio. High context windows, multimodal.

Dataflow architecture optimized for AI inference. High throughput for enterprise.

Chinese AI API hub with competitive pricing. Good for Qwen and DeepSeek models.

European cloud provider with generative AI endpoints. 1M free tokens.

Alibaba's AI platform. Extensive model library including Qwen and open-source models.

European cloud AI endpoints. Competitive pricing on open models.

Cloud for running open-source models. Easy API for Llama, Mistral, FLUX.

Inference Endpoints from Hugging Face. Managed deployment for open models.

API access to Perplexity's Sonar models. Excellent for research and factuality.

Official Mistral API. Home of Codestral, Mistral Large, and open models.

Mistral's code-specialized model. Excellent for completion and refactor tasks.

Fastest inference on custom Wafer Scale Engine hardware. Up to 1M tokens/day free.

Open source AI coding agent for VS Code, JetBrains, CLI. 500+ models.

Cloud platform for deploying full-stack AI apps. 750K+ developers.

Nous Research API portal. Home of Hermes and Dischat models.

GLM models via Z.ai. Fast coding plans from $10/month.

ByteDance's AI platform. 500K free tokens per LLM, 2M vision tokens.

Chinese AI leader with abab, M1, M2 models. Coding plans from $10/month.

Private, uncensored AI for text and image generation. No account required to try. Decentralized inference with focus on privacy and free speech.

Open-source API gateway for LLMs. Route requests to 180+ models from 60+ providers with one integration. Self-hostable with usage tracking and cost optimization.

Privacy-focused AI platform offering private access to multiple open-source models. Founded by ex-Instagram/Meta engineers. Preferred by OpenClaw users.

High-performance AI inference platform for open-source models. Founded in 2024 in Santa Clara. Optimized for cost, speed, and quality.

AI coding assistant and learning platform. Learn to code with AI-powered interactive lessons and projects.

Claude API by Anthropic. State-of-the-art reasoning models including Claude 3.5 Sonnet, Claude 4 Opus, and Claude 4.5 Haiku. Usage-based pricing with no monthly subscription required.

Fastest inference for open-source LLMs and image models. Serverless, on-demand GPU deployments, and fine-tuning on one platform. $1 free starter credits.

Run AI models directly in GitHub. Access GPT-4o, Claude, Llama, DeepSeek and more via GitHub's unified API. Free tier with rate limits, paid usage beyond.

Run open-source LLMs locally or in the cloud. Free local inference on your own hardware. Optional cloud plans for larger models with datacenter-grade GPUs.

Baidu's enterprise AI platform providing access to the ERNIE series models and other LLM capabilities through Baidu Intelligent Cloud.

Moonshot AI's Kimi platform offering trillion-parameter K2.5 and K2.6 large language models with up to 256K context window and tool calling support.

StepFun's open platform providing access to the Step family of large language models with strong reasoning and agentic capabilities.

Decentralized serverless AI compute platform on the Bittensor network offering LLM inference at highly competitive rates.

Affordable multi-model AI inference hosting service providing extremely low-cost access to large language models.

Serverless LLM inference and GPU cloud platform optimized for cost, speed, and quality with enterprise-grade infrastructure.

Low-cost subscription for open coding models. Curated and benchmarked specifically for coding agents with reliable global access.

Smart LLM routing platform that automatically selects the optimal model based on quality, cost, and speed requirements.