💬 Conversations
+ New Chat
☰
New Chat
🎯 Tokens: 0
Cost: $0.00
🇬🇧 EN
🇨🇿 CS
🇫🇷 FR
🇩🇪 DE
🇺🇦 UA
🇷🇺 RU
🧠 Qwen
🐬 Dolphin
MiMo V2 Flash (Free)
Gemma 2 9B (Free)
Llama 3.1 8B (Free)
Phi-3 Mini (Free)
Qwen 2 7B (Free)
DeepSeek V3 (Best Value)
Qwen 2.5 72B
Llama 3.3 70B
Llama 3.1 405B
Command R+ (128k)
GPT-4 Turbo
GPT-4
GPT-3.5 Turbo
Claude 3.5 Sonnet
Claude 3 Opus
Claude 3 Sonnet
Claude 3 Haiku
Gemini 1.5 Pro
Gemini 1.5 Flash
Gemini Pro
Llama 3 70B
Mistral Large
Mixtral 8x7B
WizardLM 2 8x22B
Flux.2 Klein 4B (OpenRouter)
Z-Image Turbo (fal.ai - Fastest)
Kling 2.6 Pro (5s video)
📥 Export
⚙️
🗑️
Send
⚙️ Settings
Endpoint Type
OpenRouter (100+ models)
Custom Endpoint (RunPod/Ollama/vLLM/etc)
Choose OpenRouter for easy access or custom for self-hosted models.
OpenRouter API Key
One key for 100+ models.
Get one here
fal.ai API Key (Optional - for Z-Image Turbo)
Only needed for fal.ai image models.
Get one here
Custom Endpoint URL
Base URL for your RunPod/vLLM/Ollama endpoint (with /v1 suffix)
API Key (Optional)
Some endpoints don't require authentication
Model Name
Model identifier (check your endpoint's docs)
System Prompt (Optional)
Set AI behavior and personality.
Cancel
Save