AI agents for business

What an agent needs from its infrastructure

Choose a model for each step of your agent and track requests and spending.

The models agents are built on

Current prices per million input tokens, lowest first.

What gets built on this

Examples of agent workflows you can build with these models.

How to connect an agent

Set the base URL and key in your compatible OpenAI or Anthropic client.

1. 1

   Get a key

   Create an account, fund your balance and create an API key.

2. 2

   Point the base URL at us

   Set our base URL and your key in a compatible client.

3. 3

   Route models per step

   Name the model each step needs in the `model` field. Spend per model and per key shows up in the dashboard statistics.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["API_KEY"],
    base_url="https://api.api-stock.com/api/v1",
)

response = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[{"role": "user", "content": "..."}],
    tools=tools,
)

curl https://api.api-stock.com/api/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "messages": [{"role": "user", "content": "..."}]
  }'

Frequently asked questions