Ollama

One command and the model runs on your machine. No limits, no quotas.

Ollama is the local default: one CLI, a model library, an OpenAI-compatible server on localhost:11434/v1. `ollama pull llama3.3` once, then call it like any other provider.

macOS, Linux, Windows. No quota. The request never leaves the machine unless you opt into Cloud. If you want a GUI instead, LM Studio; if you want production batching, vLLM.

Max context: Whatever your RAM allows
Free tier: Unlimited and private
Requirement: Nothing — no account

Endpoint

Base URLhttp://localhost:11434/v1

Rate limitNone — it is your machine

OpenAI-compatible
Native SDK: Ollama SDK
text
image
code
vision
reasoning

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'http://localhost:11434/v1',
  apiKey: 'not-needed'
})

const response = await client.chat.completions.create({
  model: 'llama3.3',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="llama3.3",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.3",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

npm install ollama

import { Ollama } from 'ollama'

const ollama = new Ollama({ host: 'http://localhost:11434' })

const response = await ollama.chat({
  model: 'llama3.3',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.message.content)

pip install ollama

from ollama import Client

client = Client(host="http://localhost:11434")

response = client.chat(
    model="llama3.3",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response["message"]["content"])

Worth knowing

Run `ollama pull llama3.3` once before the first request.

Models you get for free5

Llama 3.3 70Bllama-3.3-70b
Qwen 3qwen3
GPT-OSS 120Bgpt-oss-120b
DeepSeek R1deepseek-ai/DeepSeek-R1
DeepSeek V4deepseek-v4-flash