Connect Agno

Configure Agno's OpenAILike model with a custom Chat Completions endpoint.

AELDER · SERVICE BASE URL

https://aelder.dev/v1

LOCAL CONFIGURATION

Let my agent set this up

Copy this task to an agent already running on your computer. Enter your API key locally when asked.

Help me connect Agno to AELDER using this guide: https://aelder.dev/docs/agno/
Service Base URL: https://aelder.dev/v1
First inspect my installed version, active profile and configuration. Explain any mismatch with the guide before changing anything.
Use the documented local configuration or CLI method. Do not automate the GUI, install software or change permissions without asking.
Preserve existing accounts, providers, models, defaults, permissions and unrelated settings. Propose the smallest change, show a redacted diff, and back up any files before editing.
Have me enter my API key locally using the tool's secret storage or an environment variable. Never ask me to paste a key into chat, print it, or include it in a command, diff, log or commit.
Use the exact model ID I choose from my account's model list. Do not invent model IDs or assume every model supports every API format or tool feature.
Validate syntax and configuration loading before making any generation request. If there is no dry-run, say so.
Explain any proposed paid test, the model and what it sends, and ask for approval before running it. Do not send project files or private conversation history as a test.
Finish with the settings changed, checks performed and steps to restore the backup.

Agno provides an OpenAILike model for OpenAI-compatible Chat Completions endpoints. It accepts the API key, base URL and model ID directly; a separate gateway is unnecessary.

This guide assumes Agno and its openai dependency are already installed in your Python environment. Preserve the tools, storage and other settings in an existing application when changing its model.

1. Prepare the environment

Set SERVICE_BASE_URL to the Base URL above, including /v1, and SERVICE_MODEL_ID to an exact ID from the authenticated models endpoint:

export SERVICE_BASE_URL="https://aelder.dev/v1"
export SERVICE_MODEL_ID="YOUR_MODEL_ID"
printf 'Service API key: '
IFS= read -r -s SERVICE_API_KEY
printf '\n'
export SERVICE_API_KEY

The hidden key prompt works in Bash and Zsh. You can instead use your local secrets manager. Keep the literal key out of source code and agent conversations, and start Python from a process that inherits these values.

2. Configure the model

import os
from agno.agent import Agent
from agno.models.openai.like import OpenAILike

model = OpenAILike(
    id=os.environ["SERVICE_MODEL_ID"],
    api_key=os.environ["SERVICE_API_KEY"],
    base_url=os.environ["SERVICE_BASE_URL"],
)
agent = Agent(model=model)

Use the complete service model ID, including any slash. Do not add an Agno provider prefix. The client appends /chat/completions to the base URL; do not enter that full request path as base_url.

To switch models, change SERVICE_MODEL_ID and recreate the model and agent. Agno does not automatically select a model from the service catalog in this example.

3. Check configuration, then generation

Importing the packages and constructing these objects checks the local setup. To make a billable request, add and run:

agent.print_response("Reply with OK.")

Confirm the requested model and usage in your service dashboard. Agents with tools, retries or multiple turns can send more than one request.

For 401 errors, check the key and process environment. For an unknown model, compare id with /v1/models. For 404 errors, check the /v1 suffix and protocol. Agno also has Responses adapters; selecting one is a separate protocol decision.

This example establishes a text configuration. Tool calling, streaming, structured output, reasoning controls and images depend on the selected model and endpoint. Test each required feature before attaching a larger workflow; do not infer context limits or prices from framework defaults.

Sources: Agno’s OpenAI-compatible model guide and OpenAILike implementation. The native configuration was reviewed; a live service run has not been verified.

Need the key? Open your AELDER dashboard. For direct API calls, see the API reference.