Skip to main content

AI Providers

Youkore needs an LLM model to think — its brain. To use one you need an API key from a provider, or a local runtime (LM Studio, Ollama) that exposes a compatible endpoint.

The setup wizard walks you through the exact steps for the provider you pick. This section is the same content, kept online so the instructions stay up to date as provider consoles change — no app update needed.

Cloud providers (API key required)

ProviderFree tierNotes
Anthropic (Claude)NoPrepaid credits, $5 enough to start
OpenAI$5 creditPhone verification at signup
Google (Gemini)YesOpenAI-compatible endpoint
GroqYesVery fast, no card required
xAI (Grok)NoAPI activation may take a few hours
DeepInfraNoPay-per-use, many open-source models
MoonshotNoKimi K2.5, 256K context
Together AINoMany open-source models
Mistral AIYes (Experiment plan)Billing must still be enabled
CerebrasYes1M tokens/day, fastest inference
Fireworks AILimited10 RPM without a card
OpenRouterNoAggregator: hundreds of models, one key

Local runtimes (no API key)

RuntimeNotes
LM StudioDesktop app, free, GPU recommended
OllamaCLI, free, NVIDIA/AMD/Apple Silicon