OpenAI-compatible clients

Valkyrie serves models through the OpenAI Chat Completions API, so any client that lets you set a base URL and API key can talk to a Valkyrie deployment.

The three values you need

Setting	Value
Base URL	`https://valkyrie-back.azumo.com/{deployment_slug}/v1`
API key	Your deployment key (`vk_dep_`)
Model	Your deployment slug (or alias)

The deployment slug looks like deployment-{id} (for example deployment-227). With an alias, the base URL becomes https://valkyrie-back.azumo.com/{account_slug}/{alias}/v1.

Where to find them

All three at once: on the endpoint’s page, click Create a key for this endpoint. The key is shown once with environment variables (OPENAI_BASE_URL, OPENAI_API_KEY, OPENAI_MODEL) and a curl test, ready to paste. This works while the endpoint is running, paused, or off on its schedule. See Create a key for an endpoint.
The URL: the endpoint’s page shows it while the model is running.
A key: the API keys screen.

Requests succeed only while the endpoint is running. If it is Off (schedule), its badge says when it starts again; if it is paused or stopped, someone has to resume or start it. See Deployment status.

Official OpenAI SDKs

from openai import OpenAI

client = OpenAI(
    base_url="https://valkyrie-back.azumo.com/{deployment_slug}/v1",
    api_key="YOUR_VALKYRIE_API_KEY",
)

resp = client.chat.completions.create(
    model="{deployment_slug}",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://valkyrie-back.azumo.com/{deployment_slug}/v1",
  apiKey: process.env.VALKYRIE_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "{deployment_slug}",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://valkyrie-back.azumo.com/{deployment_slug}/v1",
    api_key="YOUR_VALKYRIE_API_KEY",
    model="{deployment_slug}",
)
print(llm.invoke("Hello!").content)

Anything else

Any app with an “OpenAI-compatible” or “custom OpenAI endpoint” setting works the same way, LibreChat, Open WebUI, editor plugins, and more. Set the base URL, key, and model name as above.

Set stream: true for token streaming. See Run inference for a streaming example and Errors for handling failures.

Get Started

Guides

Connect a Model

Dashboard

Security

OpenAI-compatible clients

The three values you need

Where to find them

Official OpenAI SDKs

LangChain

Anything else

Get Started

Guides

Connect a Model

Dashboard

Security

​The three values you need

​Where to find them

​Official OpenAI SDKs

​LangChain

​Anything else

The three values you need

Where to find them

Official OpenAI SDKs

LangChain

Anything else