opencode-litellm

Runtime LiteLLM model autodiscovery for OpenCode. The plugin fetches LiteLLM /model/info at OpenCode startup and adds an in-memory provider named LiteLLM by default.

Install

Install the package by npm name, then add it to OpenCode plugin config:

npm install @staticeng/opencode-litellm

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": [
    [
      "@staticeng/opencode-litellm",
      {
        "baseURL": "https://litellm.example.com/v1",
        "apiKeyEnv": "LITELLM_API_KEY"
      }
    ]
  ]
}

Set the API key in your environment before starting OpenCode:

export LITELLM_API_KEY="..."

Do not put real API keys in opencode.json. If you pass apiKey directly, the plugin uses it only in memory and never logs it, but environment variables are recommended.

Options

| Option | Default | Purpose | | --- | --- | --- | | baseURL | LITELLM_BASE_URL | LiteLLM proxy base URL. /v1 URLs are supported. | | apiKey | env value | Bearer token for LiteLLM. | | apiKeyEnv | LITELLM_API_KEY | Environment variable used when apiKey is not set. | | providerKey | LiteLLM | Key written to cfg.provider[providerKey]. | | providerName | LiteLLM | Human provider name. | | overrides | {} | Per-model deep-merge overrides. | | providerOverrides | {} | Provider-level deep-merge overrides. | | includeModes | chat, responses | LiteLLM modes to include. | | includeModels | all included modes | Optional allowlist by model name. | | excludeModels | none | Optional denylist by model name. | | timeoutMs | 30000 | /model/info request timeout. | | strict | false | Throw on fetch/mapping failures instead of warning. |

The LiteLLM key must have permission to call GET /model/info.

Overrides

LiteLLM metadata does not expose every OpenCode model field. Use overrides to add variants, thinking controls, cache costs, interleaved reasoning settings, limits, modalities, timeouts, or provider-specific options.

{
  "plugin": [
    [
      "@staticeng/opencode-litellm",
      {
        "baseURL": "https://litellm.example.com/v1",
        "apiKeyEnv": "LITELLM_API_KEY",
        "overrides": {
          "chatgpt/gpt-5.5": {
            "limit": { "context": 262144, "output": 128000 },
            "variants": {
              "high": { "options": { "reasoning_effort": "high" } }
            },
            "interleaved": { "field": "reasoning_details" }
          }
        },
        "providerOverrides": {
          "options": {
            "timeout": 600000
          }
        }
      }
    ]
  ]
}

Overrides win over generated values through a recursive deep merge. Arrays and scalar values are replaced rather than concatenated.

Runtime Behavior

• Fetches ${baseURL}/model/info with Authorization: Bearer <token>.
• Handles base URLs with or without a trailing slash, including /v1.
• Adds or replaces cfg.provider[providerKey] during OpenCode's plugin config hook.
• Does not write opencode.json, cache model metadata, or persist generated provider data.
• Includes chat and responses modes by default; non-chat modes such as embedding and rerank are excluded unless explicitly included.
• No HuggingFace fallback is included in v1.

Publish Notes

The package is ESM-only and publishes the compiled dist/ directory.

npm install
npm run build
npm test
npm pack --dry-run

Confirm package contents before publishing and keep secrets out of fixtures, docs, logs, and config examples.