> ## Documentation Index
> Fetch the complete documentation index at: https://ancplua.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Model providers

# Model providers

This page covers **LLM/model providers** (not chat channels like WhatsApp/Telegram).
For model selection rules, see [/concepts/models](/datzi/concepts/models).

## Quick rules

* Model refs use `provider/model` (example: `ollama/qwen3-coder:32b`).
* If you set `agents.defaults.models`, it becomes the allowlist.
* CLI helpers: `datzi onboard`, `datzi models list`, `datzi models set <provider/model>`.

> Datzi runs on Ollama (qwen3-coder:14b). No external API keys required.

## Built-in providers

> Datzi runs on Ollama (qwen3-coder:14b). No external API keys required.

## Providers via `models.providers` (custom/base URL)

> Datzi runs on Ollama (qwen3-coder:14b). No external API keys required.

### Ollama (recommended)

Ollama is a local LLM runtime that provides an OpenAI-compatible API:

* Provider: `ollama`
* Auth: None required (local server)
* Example model: `ollama/qwen3-coder:14b`
* Installation: [https://ollama.ai](https://ollama.ai)

```bash theme={null}
# Install Ollama, then pull the recommended model:
ollama pull qwen3-coder:14b
```

```json5 theme={null}
{
  agents: {
    defaults: {
      model: {
        primary: 'ollama/qwen3-coder:14b'
      }
    }
  }
}
```

Ollama is automatically detected when running locally at `http://127.0.0.1:11434/v1`.
See [Local models](/datzi/gateway/local-models) for model recommendations and custom configuration.

### vLLM

vLLM is a local (or self-hosted) OpenAI-compatible server:

* Provider: `vllm`
* Auth: Optional (depends on your server)
* Default base URL: `http://127.0.0.1:8000/v1`

To opt in to auto-discovery locally (any value works if your server doesn’t enforce auth):

```bash theme={null}
export VLLM_API_KEY="vllm-local"
```

Then set a model (replace with one of the IDs returned by `/v1/models`):

```json5 theme={null}
{
  agents: {
    defaults: {
      model: {
        primary: 'vllm/your-model-id'
      }
    }
  }
}
```

See [Local models](/datzi/gateway/local-models) for details on local proxy configuration.

### Local proxies (LM Studio, vLLM, LiteLLM, etc.)

Example (OpenAI‑compatible):

```json5 theme={null}
{
  agents: {
    defaults: {
      model: {
        primary: 'lmstudio/minimax-m2.1-gs32'
      },
      models: {
        'lmstudio/minimax-m2.1-gs32': {
          alias: 'Minimax'
        }
      }
    }
  },
  models: {
    providers: {
      lmstudio: {
        baseUrl: 'http://localhost:1234/v1',
        apiKey: 'LMSTUDIO_KEY',
        api: 'openai-completions',
        models: [
          {
            id: 'minimax-m2.1-gs32',
            name: 'MiniMax M2.1',
            reasoning: false,
            input: ['text'],
            cost: {
              input: 0,
              output: 0,
              cacheRead: 0,
              cacheWrite: 0
            },
            contextWindow: 200000,
            maxTokens: 8192
          }
        ]
      }
    }
  }
}
```

Notes:

* For custom providers, `reasoning`, `input`, `cost`, `contextWindow`, and `maxTokens` are optional.
  When omitted, Datzi defaults to:
  * `reasoning: false`
  * `input: ["text"]`
  * `cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }`
  * `contextWindow: 200000`
  * `maxTokens: 8192`
* Recommended: set explicit values that match your proxy/model limits.

## CLI examples

```bash theme={null}
datzi onboard --auth-choice opencode-zen
datzi models set ollama/qwen3-coder:32b
datzi models list
```

See also: [/gateway/configuration](/datzi/gateway/configuration) for full configuration examples.