Your first API request.

Bring your OpenAI or Anthropic client. Create a key, choose an active model, and send your first request.

Browse the current model catalog and rates for model IDs, modalities and published rates. Model availability and supported options can change.

Get an API key

1. Get set up

1. Create an account.
2. Verify your email. This adds $5 of free credit to your account.
3. Create an API key in the console. Keys are shown once; store yours securely.
4. Point your OpenAI client at the Actaserve base URL:

2. Make your first request

Save your key as the ACTASERVE_API_KEY environment variable. Keep it private and out of source control. These examples use aion-labs/aion-2.0 from the active public catalog; check its current rates before sending a request.

cURL

curl https://actaserve.com/v1/chat/completions \
  -H "Authorization: Bearer $ACTASERVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aion-labs/aion-2.0",
    "messages": [{"role": "user", "content": "Say hello in five words"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://actaserve.com/v1",
    api_key=os.environ["ACTASERVE_API_KEY"],
)

completion = client.chat.completions.create(
    model="aion-labs/aion-2.0",
    messages=[{"role": "user", "content": "Say hello in five words"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://actaserve.com/v1",
  apiKey: process.env.ACTASERVE_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "aion-labs/aion-2.0",
  messages: [{ role: "user", content: "Say hello in five words" }],
});
console.log(completion.choices[0].message.content);

curl https://actaserve.com/v1/images/generations \
  -H "Authorization: Bearer $ACTASERVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "black-forest-labs/flux.1-dev",
    "prompt": "a lighthouse at dawn, aerial view",
    "size": "1024x1024"
  }'

curl https://actaserve.com/v1/messages \
  -H "x-api-key: $ACTASERVE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aion-labs/aion-2.0",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "Say hello in five words"}]
  }'

Endpoints

See supported interfaces and model-dependent limits for details.

For the selected model, Actaserve orders eligible suppliers by recent failures, session continuity, routing economics, and configured priority. After a qualifying failure, Actaserve can try another eligible supplier.

Agent harnesses

Tools that support the Anthropic Messages API and honor ANTHROPIC_BASE_URL can send requests through Actaserve. Use an active model slug from GET /v1/models:

# Use an active model with a compatible harness
ANTHROPIC_BASE_URL=https://actaserve.com \
ANTHROPIC_API_KEY="$ACTASERVE_API_KEY" \
claude --model "aion-labs/aion-2.0"

Request headers

Spending limits & policy

Each key can carry a monthly spending limit, a calendar-month hard cap that returns 402 insufficient_quota after the limit, and an access policy. Allowed-model violations return 403 permission_error; blocked providers are removed from routing. Set both when creating a key in the console.

Cached-token pricing

When an upstream reports cached input tokens, Actaserve bills those tokens at 10% of the model's published input rate. Recorded cache usage appears in console usage views.

Errors

Credits

You get $5 of free credit after verifying your email. Language models are priced per token and image models per image. Live prices appear in the public model catalog. For programmatic access, use the catalog API (JSON).

Still stuck? Email us with the endpoint, model and error message. Keep API keys, prompts and customer data out of your email.