Integration
Roo Code with an LLMcode key
Roo Code is a VS Code agent that can use any OpenAI-compatible endpoint. Three fields are enough: base URL, key and model ID.
Updated
Provider settings
Choose the OpenAI Compatible provider in Roo Code. Set the base URL to https://llmcode.io/v1 and paste the LLMcode key.
The model ID is the published profile slug. You can add several profiles and switch between them during a task.
Agent safety
Roo Code can run commands and edit files. Use a dedicated key with a spend limit and enable the confirmations you need.
A coding agent can generate long contexts quickly. Start with the cheaper profile and escalate only complex steps.
Verification
Ask the agent a trivial question first. If it answers, the key and base URL are correct; the request appears in the journal.
If the model list is empty, check GET /v1/models with the same key in a terminal.
Connect
Provider: OpenAI Compatible
Base URL: https://llmcode.io/v1
API key: sk-llmcode-…
Model ID: flashPublished model prices
USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.
| Model | Input | Output | Cache |
|---|---|---|---|
| Claude Opus 5.5 | $2.70 | $8.00 | $0.14 |
| DeepSeek Flash | $0.50 | $2.00 | $0.01 |
| Claude Sonnet 5.5 | $1.33 | $6.67 | $0.07 |
| DeepSeek V4 Pro | $2.20 | $6.60 | $0.07 |
Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.
Questions
Which provider do I choose in Roo Code?
OpenAI Compatible. Enter https://llmcode.io/v1 as the base URL.
Can I use Claude models?
Yes, via the OpenAI-compatible shape if the client supports them; use the published Claude profile slug as the model ID.
How do I stop a runaway agent?
Put a spend limit on the key and keep the agent's auto-approve settings conservative.