Integration
LibreChat with LLMcode
LibreChat supports custom endpoints in librechat.yaml. Point one at LLMcode and list the published models you want to expose.
Updated
Config
Add a custom endpoint with baseURL https://llmcode.io/v1, your key and a model list. Keep the config out of a public repository.
For multi-user LibreChat deployments, decide whether each user brings a key or the server holds one shared key.
Shared key caveat
A shared server key means all users spend the same balance and the journal cannot separate people. If that matters, issue per-user keys and pass them through your own auth layer.
A spend limit on the shared key is the minimum protection.
Model list
The model IDs must be published slugs. Display names can be anything; the request uses the slug.
If LibreChat shows the endpoint but no models, compare its model list with GET /v1/models.
Connect
endpoints:
custom:
- name: "LLMcode"
apiKey: "${LLMCODE_API_KEY}"
baseURL: "https://llmcode.io/v1"
models:
default: ["deepseek-flash", "deepseek-v4-pro"]
fetch: truePublished 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
Is LibreChat officially supported?
LLMcode is protocol-compatible: any client that accepts a custom OpenAI base URL can use it. Official client support is up to the client project.
Can each user have a key?
Yes, but it requires your own authentication layer; LibreChat's custom endpoint usually holds one server-side key.
Does streaming work?
Chat streaming is supported by the API; LibreChat uses it when configured.