Integration
JetBrains IDEs with an OpenAI-compatible provider
JetBrains AI features vary by product. The reliable route to a custom endpoint is a plugin that accepts an OpenAI-compatible base URL, such as Continue.
Updated
Continue plugin
Install Continue from the JetBrains marketplace and open its configuration file. Add a model with provider openai and apiBase https://llmcode.io/v1.
Put the key in an environment variable and reference it from the config, so it is not committed with the project.
Chat and autocomplete
Continue uses separate models for chat, edit and autocomplete. A fast profile for autocomplete and a stronger one for chat keeps both latency and cost reasonable.
If the IDE shows no models, validate the key with GET /v1/models outside the IDE.
What is not covered
JetBrains' built-in AI Assistant may not accept an arbitrary base URL in every version. In that case use Continue or Proxy AI rather than trying to patch the built-in client.
Connect
models:
- name: LLMcode Flash
provider: openai
model: flash
apiBase: https://llmcode.io/v1
apiKey: $LLMCODE_API_KEYPublished 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
Does the built-in JetBrains AI Assistant work with LLMcode?
Not guaranteed: custom endpoints depend on the product and version. Continue is the predictable route.
Where do I put the key?
In an environment variable referenced by the plugin config. Do not commit it to the repository.
Can I use a different model for autocomplete?
Yes. Continue supports separate models for chat, edit and autocomplete.