N

Nexus-AI โ€” produced by AW Ihenyen

API Settings

AI

API Settings

Manage your AI provider API keys โ€” 2 providers active

โšก๐Ÿ’Ž

Groq & Gemini Ready

Both AI providers are configured and validated. Choose either in the Playground!

End-to-End Encrypted

All API keys are stored locally in your browser. Never sent to external servers.

Ready
โšก

Groq

https://api.groq.com/openai/v1

active

Available Models

llama-3.3-70b-versatilellama-3.1-8b-instantmixtral-8x7b-32768gemma2-9b-it
Rate: 30/minUsage: 0 tokens
Ready
๐Ÿ’Ž

Google Gemini

https://generativelanguage.googleapis.com/v1beta

active

Available Models

gemini-2.0-flashgemini-1.5-progemini-1.5-flash
Rate: 60/minUsage: 0 tokens
๐Ÿ”€

OpenRouter

https://openrouter.ai/api/v1

inactive

Available Models

meta-llama/llama-3-70bmistralai/mixtral-8x7bgoogle/gemma-7b
Rate: 50/minUsage: 0 tokens
๐Ÿค—

HuggingFace

https://api-inference.huggingface.co

inactive

Available Models

meta-llama/Llama-3-8Bmistralai/Mistral-7Bbigcode/starcoder2
Rate: 30/minUsage: 0 tokens
๐Ÿฆ™

Ollama (Local)

http://localhost:11434

inactive

Available Models

llama3mistralcodellamaphi3
Rate: 999/minUsage: 0 tokens
๐Ÿ”ฌ

DeepSeek

https://api.deepseek.com/v1

inactive

Available Models

deepseek-chatdeepseek-coderdeepseek-reasoner
Rate: 30/minUsage: 0 tokens
๐Ÿค

Together AI

https://api.together.xyz/v1

inactive

Available Models

meta-llama/Llama-3-70b-chatmistralai/Mixtral-8x7Bcodellama/CodeLlama-34b
Rate: 60/minUsage: 0 tokens
๐ŸŽ†

Fireworks AI

https://api.fireworks.ai/inference/v1

inactive

Available Models

llama-v3-70b-instructmixtral-8x7bfirefunction-v2
Rate: 60/minUsage: 0 tokens
๐Ÿง 

Cerebras

https://api.cerebras.ai/v1

inactive

Available Models

llama3.1-8bllama3.1-70b
Rate: 30/minUsage: 0 tokens
๐ŸŒŠ

Mistral AI

https://api.mistral.ai/v1

inactive

Available Models

mistral-large-latestmistral-mediummistral-smallcodestral
Rate: 30/minUsage: 0 tokens