Providers
39 providers. 80+ models. One API.
Core Providers
Direct API access with native authentication
OpenAI Operational
→gpt-4ogpt-4o-minigpt-4-turbo
Anthropic Operational
→claude-sonnet-4claude-opus-4
Google Operational
→gemini-2.5-progemini-2.5-flash
Mistral Operational
→mistral-largemistral-small
DeepSeek Operational
→deepseek-chatdeepseek-reasoner
Cohere Operational
→command-r-pluscommand-r
AI21 Labs Operational
→jamba-large-1jamba-mini-1
xAI / Grok Operational
→grok-3grok-3-mini
High-Performance Inference
Ultra-fast inference with free tiers
Cloud Inference Platforms
Scalable inference with pay-as-you-go pricing
Together AI Operational
→llama-3.3-70b-turbodeepseek-v3
Fireworks AI Operational
→llama-3.3-70bdeepseek-v3
DeepInfra Operational
→llama-3.3-70bdeepseek-v3
Novita AI Operational
→llama-3.3-70bdeepseek-r1
Lepton AI Operational
→llama-3.3-70bqwen-72b
Hyperbolic Operational
→llama-3.3-70bdeepseek-v3
Anyscale Operational
→llama-3.1-70b
Baseten Operational
→deepseek-v3
Replicate Operational
→llama-3.3-70b
Featherless AI Operational
→llama-3.3-70b
Mancer Operational
→mythomax-l2-13b
Gateways & Routers
Aggregators that proxy multiple providers
Chinese Ecosystem
Providers from the Chinese AI ecosystem
Alibaba / Qwen Operational
→qwen-turboqwen-plusqwen-max
Zhipu AI / GLM Operational
→glm-4-flashglm-4-plus
Baidu / ERNIE Operational
→ernie-speed-128kernie-4.0
Tencent / Hunyuan Operational
→hunyuan-standard
ByteDance / Doubao Operational
→doubao-pro-256kdoubao-lite-128k
Moonshot AI / Kimi Operational
→moonshot-v1-128k
01.AI / Yi Operational
→yi-34b-chat
MiniMax Operational
→abab6.5-chat
Local / Self-Hosted
Run models on your own infrastructure