Skip to main content

Aider

Connect Aider to Divyam with its OpenAI-compatible settings.

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.

1. Install Aider​

Follow the official installation instructions.

2. Add the model settings​

divyam-as/

Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing

Connection and model names

This setup redirects Aider's built-in OpenAI connection to Divyam for this launch. Aider selects the OpenAI-compatible adapter with openai/divyam-as/gpt-6-sol. The adapter removes the leading openai/ and sends divyam-as/gpt-6-sol as the API model ID. The files below describe Aider's model settings and do not register a separate provider.

In your project root, create .aider.model.settings.yml:

- name: openai/divyam-as/gpt-6-sol
  use_temperature: false
  extra_params:
    max_tokens: 8192

Create .aider.model.metadata.json alongside it:

{
  "openai/divyam-as/gpt-6-sol": {
    "max_input_tokens": 200000,
    "max_output_tokens": 8192,
    "max_tokens": 200000,
    "mode": "chat",
    "supports_function_calling": false,
    "supports_vision": false
  }
}

These native model settings omit the temperature parameter.

3. Send your first prompt​

From the folder containing your model settings, start Aider:

OPENAI_API_BASE="https://api.preview.divyam.ai/v1" \
OPENAI_API_KEY="divyam-sw-v1-..." \
aider --model openai/divyam-as/gpt-6-sol \
  --weak-model openai/divyam-as/gpt-6-sol

The inline values apply to this launch and leave existing shell OpenAI settings unchanged.

In Aider's composer
Hello, what are your capabilities?
Paste this message, then send it.
Feature limits

This setup uses whole-file text edits without model function tools. Add --no-auto-commits if you want to review changes before committing. Check charges in the Divyam console.

Images

With an image-capable model, set supports_vision to true in its .aider.model.metadata.json entry. Reopen Aider, then use /add screenshot.png to attach a local image.

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.