Providers
Connect 20+ language model providers with your own keys, or stay fully local. Keys live in this browser session only.
OpenAI
Realtime voice and tool calling
Models
gpt-4.1gpt-4o-mini
Anthropic Claude
Long context reasoning
Models
claude-sonnet-4.5claude-haiku-4.5
DeepSeek
Low cost reasoning
Models
deepseek-chatdeepseek-reasoner
Google Gemini
Multimodal input
Models
gemini-2.5-flashgemini-2.5-pro
Mistral
European hosting
Models
mistral-largemistral-small
Groq
Fastest token stream
Models
llama-3.3-70bqwen-2.5-32b
xAI Grok
Live web awareness
Models
grok-4grok-4-mini
OpenRouter
One key, many models
Models
auto
Together
Open weight hosting
Models
llama-3.1-405b
Fireworks
Serverless open models
Models
qwen3-235b
Perplexity
Search grounded answers
Models
sonar-pro
Cohere
Retrieval focused
Models
command-a
WebGPU in browser
Runs fully on your device
Models
qwen3-1.7bllama-3.2-3b
Ollama
Local daemon on localhost
Models
llama3.2qwen2.5
LM Studio
OpenAI compatible server
Models
any loaded model
llama.cpp server
Bring your own weights
Models
gguf models
vLLM
High throughput self hosting
Models
self hosted