Files
opencode/packages/web/src/content/docs/docs/models.mdx
T
2025-07-19 12:45:33 -04:00

203 lines
4.3 KiB
Plaintext

---
title: Models
description: Configuring an LLM provider and model.
---
opencode uses the [AI SDK](https://ai-sdk.dev/) and [Models.dev](https://models.dev) to support for **75+ LLM providers** and it supports running local models.
---
## Providers
You can configure providers in your opencode config under the `provider` section.
---
### Defaults
Most popular providers are preloaded by default. If you've added the credentials for a provider through `opencode auth login`, they'll be available when you start opencode.
---
### Custom
You can add custom providers by specifying the npm package for the provider and the models you want to use.
```json title="opencode.json" {5,9-11}
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"moonshot": {
"npm": "@ai-sdk/openai-compatible",
"options": {
"baseURL": "https://api.moonshot.ai/v1"
},
"models": {
"kimi-k2-0711-preview": {}
}
}
}
}
```
---
### Base URL
You can customize the base URL for any provider by setting the `baseURL` option. This is useful when using proxy services or custom endpoints.
```json title="opencode.json" {6}
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"anthropic": {
"options": {
"baseURL": "https://api.anthropic.com/v1"
}
}
}
}
```
---
### OpenRouter
Many OpenRouter models are preloaded by default - you can customize these or add your own.
Here's an example of specifying a provider
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"openrouter": {
"models": {
"moonshotai/kimi-k2": {
"options": {
"provider": {
"order": ["baseten"],
"allow_fallbacks": false
}
}
}
}
}
}
}
```
You can also add additional models
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"openrouter": {
"models": {
"somecoolnewmodel": {},
}
}
}
}
```
---
### Local
You can configure local model like ones served through LM Studio or Ollama. To
do so, you'll need to specify a couple of things.
Here's an example of configuring a local model from LM Studio:
```json title="opencode.json" {4-15}
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"lmstudio": {
"npm": "@ai-sdk/openai-compatible",
"name": "LM Studio (local)",
"options": {
"baseURL": "http://127.0.0.1:1234/v1"
},
"models": {
"google/gemma-3n-e4b": {
"name": "Gemma 3n-e4b (local)"
}
}
}
}
}
```
In this example:
- `lmstudio` is the custom provider ID. We'll use this later.
- `npm` specifies the package to use for this provider. Here, `@ai-sdk/openai-compatible` is used for any OpenAI-compatible API.
- `name` is the display name for the provider in the UI.
- `options.baseURL` is the endpoint for the local server.
- `models` is a map of model IDs to their configurations. The model name will be displayed in the model selection list.
Similarly, to configure a local model from Ollama:
```json title="opencode.json" {5,7}
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"ollama": {
"npm": "@ai-sdk/openai-compatible",
"options": {
"baseURL": "http://localhost:11434/v1"
},
"models": {
"llama2": {}
}
}
}
}
```
To set one of these as the default model, you can set the `model` key at the
root.
```json title="opencode.json" {3}
{
"$schema": "https://opencode.ai/config.json",
"model": "lmstudio/google/gemma-3n-e4b"
}
```
Here the full ID is `provider_id/model_id`, where `provider_id` is the key in the `provider` list we set above and `model_id` is the key from the `provider.models` list.
---
## Select a model
If you have multiple models, you can select the model you want by typing in:
```bash frame="none"
/models
```
---
## Loading models
When opencode starts up, it checks for the following:
1. The model list in the opencode config.
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"model": "anthropic/claude-sonnet-4-20250514"
}
```
The format here is `provider/model`.
2. The last used model.
3. The first model using an internal priority.