ld
Clients

Endpoints & SDKs

Point any OpenAI- or Anthropic-compatible client at the gateway.

llama-dash speaks the OpenAI and Anthropic /v1/* wire formats, so most clients need only a base-URL change and a llama-dash API key. The dashboard's Endpoints page generates ready-to-paste snippets for curl, Python, TypeScript, Home Assistant, Claude Code, opencode, Continue, and Open WebUI.

Base URL and key

SettingValue
Base URLhttp://<llama-dash-host>:3000/v1
AuthAuthorization: Bearer sk-... (required once API keys exist)

Examples

curl http://localhost:3000/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"your-model-id","messages":[{"role":"user","content":"Hello!"}]}'
from openai import OpenAI

client = OpenAI(base_url="http://localhost:3000/v1", api_key="sk-...")
resp = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:3000/v1",
  apiKey: "sk-...",
});
const resp = await client.chat.completions.create({
  model: "your-model-id",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Other clients

  • Continue / Open WebUI — set the OpenAI-compatible base URL to http://<host>:3000/v1 and paste a llama-dash key.
  • Home Assistant — use the OpenAI conversation integration pointed at the same base URL.
  • Claude Code & Anthropic SDKs — see Claude Code passthrough.
  • OpenCode with a ChatGPT subscription — see OpenCode & ChatGPT passthrough.

The Endpoints page in the dashboard pre-fills your host, a selected model, and a key, so you can copy a working snippet directly.

Last updated on

On this page