Live pricing
Check input, output, and capability pricing before larger usage.
TackleKey
OpenAI SDK integration
Point the OpenAI SDK at TackleKey with base_url
Many OpenAI SDK compatible clients can be tested by changing three things: base URL, project API key, and model name. Start with one small request, then check logs and balance records.
Minimal configuration example
from openai import OpenAI
client = OpenAI(
api_key="tk-project-key",
base_url="https://api.tacklekey.com/v1",
)
response = client.chat.completions.create(
model="openai/gpt-4o-mini",
messages=[{"role": "user", "content": "Return one health-check sentence."}],
max_tokens=64,
)
print(response.choices[0].message.content)Configuration checklist
| Item | How to verify |
|---|---|
| Base URL | Use https://api.tacklekey.com/v1, not the console URL. |
| Project key | Use a project API key created in the TackleKey console and keep it server-side. |
| Model name | Copy the current model name from live pricing or a model detail page. |
| Logs | After the first request, inspect logs and balance records before sending a batch. |
Next steps
Examples hub
Copy cURL, Node.js, Python, or client configuration examples.
Troubleshooting
Debug 401, 429, invalid model, base URL, and billing issues.
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.