> ## Documentation Index
> Fetch the complete documentation index at: https://sure-917046f5-docs-cloudflare-tunnel-self-hosting.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM support

> Configure AI features with local or cloud models

<Note>
  LLM usage is optional and must be explicitly configured. You can maintain full control by running local models on your own systems through Ollama, LM Studio, or similar tools. No data is sent to external services unless you configure a cloud provider.
</Note>

## Configuration via settings

Configure AI settings through the web interface:

1. Go to **Settings** → **Self-Hosting**
2. Scroll to the **AI Provider** section
3. Configure:
   * **OpenAI Access Token** - Your API key
   * **OpenAI URI Base** - Custom endpoint (leave blank for OpenAI)
   * **OpenAI Model** - Model name (required for custom endpoints)

Settings in the UI override environment variables.

## OpenAI compatible API

Sure supports any OpenAI-compatible API endpoint, giving you flexibility to use:

* **OpenAI** - Direct access to GPT models
* **Ollama** - Run models locally on your hardware
* **LM Studio** - Local model hosting with a GUI
* **OpenRouter** - Access to multiple providers (Anthropic, Google, etc.)
* **Other providers** - Groq, Together AI, Anyscale, Replicate, and more

### OpenAI

```bash theme={null}
OPENAI_ACCESS_TOKEN=sk-proj-...
# No other configuration needed
```

Recommended models:

* `gpt-4.1` - Default, best balance of speed and quality
* `gpt-5` - Latest model, highest quality
* `gpt-4o-mini` - Cheaper, good quality

### Ollama (local)

```bash theme={null}
# Dummy token (Ollama doesn't need authentication)
OPENAI_ACCESS_TOKEN=ollama-local

# Ollama API endpoint
OPENAI_URI_BASE=http://localhost:11434/v1

# Model you pulled
OPENAI_MODEL=llama3.1:13b
```

Install and run Ollama:

```bash theme={null}
# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.com/install.sh | sh

# Start Ollama
ollama serve

# Pull a model
ollama pull llama3.1:13b
```

### LM Studio (local)

1. Download from [lmstudio.ai](https://lmstudio.ai/)
2. Download a model through the UI
3. Start the local server
4. Configure Sure:

```bash theme={null}
OPENAI_ACCESS_TOKEN=lmstudio-local
OPENAI_URI_BASE=http://localhost:1234/v1
OPENAI_MODEL=your-model-name
```

### OpenRouter

Access multiple providers through a single API:

```bash theme={null}
OPENAI_ACCESS_TOKEN=your-openrouter-api-key
OPENAI_URI_BASE=https://openrouter.ai/api/v1
OPENAI_MODEL=google/gemini-2.0-flash-exp
```

Recommended models:

* `google/gemini-2.5-flash` - Fast and capable
* `anthropic/claude-sonnet-4.5` - Excellent reasoning
* `anthropic/claude-haiku-4.5` - Fast and cost-effective

## Token budget

Sure applies a token budget to every outbound LLM call — chat history, auto-categorization, merchant detection, and PDF processing. The defaults are conservative (2048-token context window) so small-context local models like Ollama work out of the box. If you use a cloud provider or a larger-context local model, raise these values.

### Configure via settings UI

1. Go to **Settings** → **Self-Hosting**
2. Scroll to the **AI Provider** section
3. Under **Token Budget**, configure:
   * **Context Window** — total tokens the model accepts (default: `2048`)
   * **Max Response Tokens** — tokens reserved for the model's reply (default: `512`)
   * **Max Items Per Batch** — upper bound for auto-categorize and merchant detection batches (default: `25`)

### Configure via environment variables

Environment variables take precedence over the settings UI.

| Variable                    | Description                                                                                                                              | Default |
| --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| `LLM_CONTEXT_WINDOW`        | Total tokens the model will accept                                                                                                       | `2048`  |
| `LLM_MAX_RESPONSE_TOKENS`   | Tokens reserved for the model's reply                                                                                                    | `512`   |
| `LLM_MAX_HISTORY_TOKENS`    | Maximum tokens for conversation history. Derived automatically if unset (`context_window - max_response_tokens - system_prompt_reserve`) | Derived |
| `LLM_SYSTEM_PROMPT_RESERVE` | Tokens reserved for the system prompt                                                                                                    | `256`   |
| `LLM_MAX_ITEMS_PER_CALL`    | Upper bound on auto-categorize / merchant detection batch size                                                                           | `25`    |

<Note>
  Large batches of transactions are automatically sliced to fit the configured context window. You no longer need to worry about the previous 25-item hard limit — it is now a soft default that adapts to your model's capacity.
</Note>

### Recommended values

| Setup                         | Context window    | Max response tokens | Max items per batch |
| ----------------------------- | ----------------- | ------------------- | ------------------- |
| Ollama / small local models   | `2048` (default)  | `512` (default)     | `25` (default)      |
| Cloud OpenAI (gpt-4.1, gpt-5) | `16384` or higher | `4096`              | `50`                |
| Large-context local models    | `8192`            | `2048`              | `50`                |

## Responses API routing

Sure automatically routes chat requests to the OpenAI Responses API when using the official OpenAI endpoint, and falls back to the Chat Completions API for custom providers. You can override this behavior with the `OPENAI_SUPPORTS_RESPONSES_ENDPOINT` environment variable.

| Variable                             | Description                                                                                                                  | Default       |
| ------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------- | ------------- |
| `OPENAI_SUPPORTS_RESPONSES_ENDPOINT` | Set to `true` to force the Responses API on a custom provider, or `false` to force the Chat Completions API on all providers | Auto-detected |

## AI cache management

Sure caches AI-generated results (like auto-categorization and merchant detection) to avoid redundant API calls and costs.

### What is the AI cache?

When AI rules process transactions, Sure stores:

* **Enrichment records** - Which attributes were set by AI (category, merchant, etc.)
* **Attribute locks** - Prevents rules from re-processing already-handled transactions

This caching means:

* Transactions won't be sent to the LLM repeatedly
* Your API costs are minimized
* Processing is faster on subsequent rule runs

### When to reset the AI cache

You might want to reset the cache when:

* **Switching LLM models** - Different models may produce better categorizations
* **Improving prompts** - After system updates with better prompts
* **Fixing miscategorizations** - When AI made systematic errors
* **Testing** - During development or evaluation of AI features

<Warning>
  Resetting the AI cache will cause all transactions to be re-processed by AI rules on the next run. This **will incur API costs** if using a cloud provider.
</Warning>

### How to reset the AI cache

**Via UI (recommended):**

1. Go to **Settings** → **Rules**
2. Click the menu button (three dots)
3. Select **Reset AI cache**
4. Confirm the action

The cache is cleared asynchronously in the background.

**Automatic reset:**

The AI cache is automatically cleared for all users when the OpenAI model setting is changed. This ensures that the new model processes transactions fresh.

### What happens when cache is reset

* **AI-locked attributes are unlocked** - Transactions can be re-enriched
* **AI enrichment records are deleted** - The history of AI changes is cleared
* **User edits are preserved** - If you manually changed a category after AI set it, your change is kept

## Evaluation system

Test and compare different LLMs for your specific use case. The eval system helps you benchmark models for transaction categorization, merchant detection, and chat assistant functionality.

See the [evaluation framework](/evals) documentation for details on:

* Running evaluations
* Comparing models
* Creating custom datasets
* Langfuse integration for tracking experiments

## Additional environment variables

These optional variables fine-tune the behavior of the OpenAI-compatible provider.

| Variable                             | Description                                                  | Default       |
| ------------------------------------ | ------------------------------------------------------------ | ------------- |
| `OPENAI_ACCESS_TOKEN`                | API key for the provider                                     | —             |
| `OPENAI_URI_BASE`                    | Custom endpoint URL (leave blank for OpenAI)                 | —             |
| `OPENAI_MODEL`                       | Model name (required for custom endpoints)                   | `gpt-4.1`     |
| `OPENAI_REQUEST_TIMEOUT`             | HTTP timeout in seconds. Raise for slow local models         | `60`          |
| `OPENAI_SUPPORTS_PDF_PROCESSING`     | Set to `false` for endpoints without vision support          | `true`        |
| `OPENAI_SUPPORTS_RESPONSES_ENDPOINT` | Override Responses API vs Chat Completions routing           | Auto-detected |
| `LLM_JSON_MODE`                      | JSON output mode: `auto`, `strict`, `json_object`, or `none` | —             |

See [Token budget](#token-budget) for `LLM_CONTEXT_WINDOW`, `LLM_MAX_RESPONSE_TOKENS`, and related variables.

## Docker compose example

### Basic Ollama setup

```yaml theme={null}
services:
  sure:
    environment:
      - OPENAI_ACCESS_TOKEN=ollama-local
      - OPENAI_URI_BASE=http://ollama:11434/v1
      - OPENAI_MODEL=llama3.1:13b
      # Optional: raise token budget for larger-context models
      # - LLM_CONTEXT_WINDOW=8192
      # - LLM_MAX_RESPONSE_TOKENS=2048
      # - LLM_MAX_ITEMS_PER_CALL=50
    depends_on:
      - ollama

  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    # Uncomment if you have an NVIDIA GPU
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

volumes:
  ollama_data:
```

### Advanced AI setup with OpenClaw

For advanced AI features including code execution and tool use, you can use the `local-ai` profile with OpenClaw:

```yaml theme={null}
services:
  sure:
    profiles:
      - local-ai
    environment:
      - OPENAI_ACCESS_TOKEN=ollama-local
      - OPENAI_URI_BASE=http://openclaw:8080/v1
      - OPENAI_MODEL=llama3.1:13b
    depends_on:
      - openclaw
      - ollama

  openclaw:
    image: openclaw/openclaw:latest
    profiles:
      - local-ai
    ports:
      - "8080:8080"
    environment:
      - OLLAMA_HOST=http://ollama:11434
    depends_on:
      - ollama

  ollama:
    image: ollama/ollama:latest
    profiles:
      - local-ai
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama

volumes:
  ollama_data:
```

To use the local AI setup:

```bash theme={null}
# Start with local AI profile
docker compose --profile local-ai up

# Or include it with other profiles
docker compose --profile local-ai --profile external-assistant up
```

The `local-ai` profile includes:

* **Ollama** - Local LLM inference
* **OpenClaw** - Gateway providing enhanced AI capabilities and tool use
* Automatic routing between Sure and the AI stack