DEVELOPER FIELD NOTES / DOCS CHECKED 2026-09-23

Ollama · local
API endpoint & setup.

Start Ollama and download a model first. localhost refers to the machine running your code. The local OpenAI SDK requires a key value, but Ollama ignores it; use ollama.

SDK base URL

Full request endpoint · POST

Read the official Ollama · local documentation ↗ · Checked 2026-09-23; no live API call made.

A small starting point.

Start Ollama locally and download your chosen model. Set AI_MODEL to its exact installed name; replace YOUR_MODEL_ID in cURL. The placeholder SDK key ollama is not a secret.

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    api_key="ollama",
    base_url="http://localhost:11434/v1",
)
response = client.chat.completions.create(
    model=os.environ["AI_MODEL"], messages=[{"role": "user", "content": "Hello!"}]
)
print(response)

// npm install openai
// Server-side Node.js; never expose API keys in a browser.
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "ollama",
  baseURL: "http://localhost:11434/v1",
});
const response = await client.chat.completions.create({
  "model": process.env.AI_MODEL,
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
});
console.log(response);

curl 'http://localhost:11434/v1/chat/completions' \
  -H "Content-Type: application/json" \
  --data '{
  "model": "YOUR_MODEL_ID",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'