Skip to main content

Python

Use the OpenAI Python SDK with Divyam's Chat Completions endpoint. You only change the base URL, the API key and the model.

Before you start

You need a Divyam account and an API key. If you don't have them yet, follow Getting Started first.

Replace the shortened divyam-sw-v1-... shown in examples with your complete API key.

The examples use divyam-as/gpt-6-sol. For another model, select its current ID in your harness or copy it from Models and pricing, and check its context limit and supported features.

Install the SDK​

The OpenAI Python SDK needs Python 3.10 or later. In your application's Python environment, run:

python3 -m pip install openai

Set your connection​

In Bash, run:

export DIVYAM_BASE_URL='https://api.preview.divyam.ai/v1'
export DIVYAM_MODEL='divyam-as/gpt-6-sol'
read -rsp 'Divyam API key: ' DIVYAM_API_KEY
printf '\n'
export DIVYAM_API_KEY

Paste your key at the prompt and press Enter. It stays hidden. Run the example from this terminal, because a new terminal needs the variables set again. In a deployed application, use your existing secret and environment settings instead.

Send a request​

Save this as first_request.py:

"""Send a first Chat Completions request through Divyam."""

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DIVYAM_API_KEY"],
    base_url=os.environ["DIVYAM_BASE_URL"],
)
response = client.chat.completions.create(
    model=os.environ["DIVYAM_MODEL"],
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)

Run it:

python3 first_request.py

The answer prints in your terminal.

Connect your application​

Use the same client settings in the backend code that calls the model. Keep your own messages, conversation history and tool-result handling, and send DIVYAM_MODEL as the model on every request. Picking a model in the console doesn't change what your code sends.

For an async backend, create AsyncOpenAI with the same api_key and base_url, and await client.chat.completions.create(...).

Chat Completions only

Divyam uses the Chat Completions API. Code built on the Responses API or native Anthropic Messages needs to move to client.chat.completions.

Check your requests​

Open the Divyam console and select Logs. Your requests appear there within a few seconds, newest first, with their status, token counts and latency. Usage and Credits & Billing catch up within a few minutes.

Local cost estimates

Some clients display zero when model prices are missing. Check Credits & Billing for Divyam charges. Local dollar limits depend on the client's price and usage data.

For filters, cached-token counts and the requested-versus-routed view, see Logs and usage.

For errors, see Troubleshooting. To replace a key, see API keys.