Ollama

Direct

Run open-source LLMs locally or in the cloud. Free local inference on your own hardware. Optional cloud plans for larger models with datacenter-grade GPUs.

Visit Ollama →

Browse all plans View promo codes Cost calculator

Provider Info

"Rate Limits" Local: unlimited. Cloud: 1 concurrent model (Free)

"Available Models (6)"

Llama 3.3

Qwen 2.5

DeepSeek V3

Mistral

Gemma 2

Phi-4

Subscription Plans

Free

$0/mo

1 cloud model at a time, Light usage

Local inference · Cloud models

Pro

$20.00/mo

3 cloud models at a time, 50x more than Free

Larger cloud models · Upload private models

Max

$100.00/mo

10 cloud models at a time, 5x more than Pro

Maximum cloud usage · Priority access

"Free Tier Available"

Free local inference, 1 cloud model at a time — No credit card required