Skip to main content

ForgeCode

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 ForgeCode and connect the provider​

Saved connection

These steps replace the URL and key on Forge's saved openai_compatible Chat connection with Divyam's values. Later Forge sessions that select this provider ID use Divyam.

Install ForgeCode using the official instructions, then connect the Chat provider:

forge provider login openai_compatible

Enter https://api.preview.divyam.ai/v1 for OPENAI_URL and your Divyam API key (divyam-sw-v1-...) when asked.

divyam-as/

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

Select divyam-as/gpt-6-sol from the discovered models.

2. Select the model and reply settings​

forge config set model openai_compatible divyam-as/gpt-6-sol

In the generated ~/.forge/.forge.toml, merge these fields into their existing sections:

temperature = 1.0
max_tokens = 8192

Keep the Chat provider openai_compatible for Divyam.

3. Start an interactive session​

From your project folder, run:

forge
In ForgeCode's composer
Hello, what are your capabilities?
Paste this message, then send it.
Images

For an image-capable model, merge this provider entry into ~/.forge/.forge.toml:

[[providers]]
id = "openai_compatible"
url = "{{OPENAI_URL}}/chat/completions"
response_type = "OpenAI"

[[providers.models]]
id = "divyam-as/gpt-6-sol"
input_modalities = ["text", "image"]

Restart Forge, then attach a local image with @[path/to/image.png].

Conversation history

Use :compact to shorten the current conversation. Automatic title generation can fail while the conversation continues.

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.