AI Providers

Access 650 models from 50 leading AI providers through our unified API

50 Providers
650 Models
Headquarters
Compliance
View models
Azure
Microsoft Azure - enterprise-grade OpenAI-compatible models
52models
View models
OpenAI
OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits all of humanity.
49models
View models
Alibaba Cloud
Alibaba Cloud's Qwen large language models with OpenAI-compatible API
48models
View models
NovitaAI
NovitaAI's OpenAI-compatible large language models
40models
View models
Google AI Studio
Google AI Studio is a platform for accessing Google's Gemini models.
32models
View models
Tencent Cloud
Tencent Cloud's TokenHub model gateway, serving Tencent's own Hunyuan models alongside third-party models through a single OpenAI-compatible API.
31models
View models
Google Vertex AI
Google Vertex AI is a platform for accessing Google's Gemini models via Vertex AI.
30models
View models
DeepInfra
DeepInfra inference platform with OpenAI-compatible API for hosting open-source models.
29models
View models
AWS Bedrock
Amazon Bedrock - fully managed service for foundation models
25models
View models
Z AI
Z AI's OpenAI-compatible large language models
19models
View models
Anthropic
Anthropic is a research and deployment company focused on building safe and useful AI.
17models
View models
Mistral AI
Mistral AI's large language models
16models
View models
Together AI
Together AI is a platform for running large language models in the cloud with fast inference.
16models
View models
ByteDance
ByteDance's ModelArk platform with OpenAI-compatible API for large language models
16models
View models
xAI
xAI's Grok large language models
15models
View models
MiniMax
MiniMax's large language models with advanced reasoning and coding capabilities
14models
View models
SCX.ai
SCX.ai is an Australian sovereign AI platform providing OpenAI-compatible general-purpose inference endpoints for a range of open models and SCX's own models, hosted on renewable-powered infrastructure.
14models
🇦🇺AUNo trainingWebsite
View models
Vertex AI (Anthropic)
Access Claude models via Google Cloud Vertex AI with the Anthropic Messages API.
12models
View models
CanopyWave
CanopyWave is a platform for running large language models with OpenAI-compatible API
11models
View models
Fireworks AI
Fireworks AI serves open-weight models on a fast, OpenAI-compatible inference platform.
11models
View models
Runware
Runware provides fast, cost-efficient inference for open and frontier LLMs through an OpenAI-compatible API.
11models
🇬🇧GBNo trainingWebsite
View models
Baidu
Baidu's Qianfan platform serving DeepSeek, GLM, Kimi, MiMo, and Hy3 models
View models
Inference.net
Inference.net is a platform for running large language models in the cloud.
View models
FlexAI
Inference cloud serving 30+ open models (DeepSeek v4.1 flash, GLM, Qwen, Gemma, gpt-oss etc) on an OpenAI-compatible API. Chat, Vision, Media, Rerank and Moderation models, with tool calling and an optional EU endpoint for sovereign users. SOC 2, zero data retention.
10models
View models
Azure Anthropic
Anthropic Claude models on Microsoft Foundry via the Anthropic Messages API
9models
View models
AWS Mantle
OpenAI frontier models on Amazon Bedrock's Mantle and Runtime Responses APIs
8models
View models
AtlasCloud
AtlasCloud provides unified APIs for video, image, audio, and language generation models.
7models
View models
Moonshot AI
Moonshot AI's OpenAI-compatible large language models
7models
View models
Meta
Meta's Model API serving Muse reasoning and image models via an OpenAI-compatible API
6models
View models
ElevenLabs
ElevenLabs provides lifelike, low-latency text-to-speech and speech-to-text models in 70+ languages.
6models
View models
Consensus Protocol
Consensus Protocol serves open-weight large language models on dedicated GPU hardware it operates, via an OpenAI-compatible inference API.
6models
View models
fal
fal is a platform for generative media inference.
5models
View models
DeepSeek
DeepSeek's high-performance language models with OpenAI-compatible API
View models
TypeSafe AI
TypeSafe AI serves Jev, a System One decision model that answers typed questions about a state with calibrated probabilities instead of generated text.
5models
View models
Reka AI
5models
View models
Vertex AI (OpenAI-compatible)
Access partner models (e.g. xAI Grok) via Google Cloud Vertex AI's OpenAI-compatible Chat Completions endpoint.
4models
View models
Groq
Groq's ultra-fast LPU inference with various models
4models
View models
Runpod
Runpod's serverless public inference endpoints
View models
Sakana AI
Sakana AI's Fugu multi-agent orchestration models, served through a single OpenAI-compatible API.
View models
Greenference
Greenference is a European open-weight LLM provider with Solar powered datacenters
4models
View models
Entrim
Entrim has its own data center in the EU, running custom-built hardware and software engineered for high throughput and cost efficiency. Zero Data Retention by default: your prompts and outputs are never stored or used for training.
4models
No trainingWebsite
View models
Perplexity
Perplexity's AI models for search and conversation with real-time web access
3models
View models
Xiaomi
Xiaomi MiMo API Open Platform provides access to the MiMo series of large language models.
3models
View models
Cloudflare
Cloudflare Workers AI runs open-weight models on Cloudflare's global GPU network through an OpenAI-compatible API.
3models
View models
SCX.ai (Turbo)
SCX.ai is an Australian sovereign AI platform providing OpenAI-compatible Turbo inference endpoints — up to 4x faster than comparable providers — for a range of open models and SCX's own models, hosted on renewable-powered infrastructure.
3models
🇦🇺AUNo trainingWebsite
View models
Meta Contributor
Meta's discounted, training-eligible Model API tier for Muse models
View models
Sciforium
Sciforium runs open-weight models on its own AMD GPU infrastructure delivering faster and cost effective inference with an OpenAI-compatible API.
2models
View models
Cerebras
Cerebras high-performance inference with ultra-fast throughput
1model
View models
Nebius AI
Nebius AI Studio - OpenAI-compatible API for large language models
1model
View models
Luminal
DeepSeek v4.1 Flash