cURL example

Test TackleKey with one cURL request

Use this raw HTTP check before debugging SDK behavior. It verifies your base URL, API key, model name, and response path.

Create account All examples

Example

#!/usr/bin/env bash
set -euo pipefail

: "${TACKLEKEY_API_KEY:?Set TACKLEKEY_API_KEY first}"

curl https://api.tacklekey.com/v1/chat/completions \
  -H "Authorization: Bearer ${TACKLEKEY_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      { "role": "user", "content": "Reply with a short API health check." }
    ]
  }'

After it works

Check request logs

Confirm the request appears under your project key and that errors are understandable.

Check balance records

Make sure usage is visible before sending larger batches or customer traffic.

Confirm model pricing

Open live pricing and verify the model before scaling.

Keep API keys server-side. Do not publish keys in frontend bundles, GitHub repositories, screenshots, logs, or issue comments.

FAQ

Which base URL should I use?

Use https://api.tacklekey.com/v1 for OpenAI-compatible chat completion requests unless your console or docs show a different project-specific endpoint.

Which model should I test first?

Start with a model visible on the live pricing page, such as the example model shown here, then switch to the model your application actually needs.

What should I check after the first response?

Check request logs, balance records, model pricing, and any errors before increasing traffic.

Try TackleKey with one OpenAI-compatible change

Create an account, generate a project API key, then replace your client base URL with the TackleKey endpoint. Keep keys server-side and verify live pricing before scaling traffic.

Create account Run first request