Mistral Vibe
Use Mistral Vibe with Divyam for file edits and shell commands.
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 Mistral Vibe
Follow the official installation instructions for version 2.26.1.
Set your key in the shell you will use to start the app:
export DIVYAM_API_KEY="divyam-sw-v1-..."
2. Configure Divyam
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
Merge this into ~/.vibe/config.toml, keeping the top-level settings above the tables:
active_model = "divyam"
[[providers]]
name = "divyam"
api_base = "https://api.preview.divyam.ai/v1"
api_key_env_var = "DIVYAM_API_KEY"
[[models]]
name = "divyam-as/gpt-6-sol"
provider = "divyam"
alias = "divyam"
temperature = 1.0
max_context_length = 200000
max_output_tokens = 8192
Keep temperature = 1.0 for this model.
3. Send your first prompt
Start Vibe from the shell where you exported the key:
vibe
Hello, what are your capabilities?
For an image-capable model, add supports_images = true to the Divyam [[models]] entry in ~/.vibe/config.toml. To turn off automatic session titles, add session_logging.generate_titles = false above the provider and model tables.
Divyam can omit the final finish_reason on capped streams, which can leave Vibe waiting or retrying. Keep the 8192-token output limit.
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.
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.