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

# Models Reference

> Available AI models and their capabilities

Reliant supports models from multiple providers. Use the model ID in workflow configurations and presets.

> **Note:** Reliant has been most extensively tested with **Anthropic** and **OpenAI** models. You may encounter issues when using other providers.

## Model Tags

Models are tagged to help with selection. You can also [bring your own model](/settings/model-config#custom-models) with your own provider.

| Tag         | Description                       |
| ----------- | --------------------------------- |
| `flagship`  | Most capable models, best quality |
| `moderate`  | Balance of capability and cost    |
| `fast`      | Optimized for speed               |
| `cheap`     | Low cost per token                |
| `reasoning` | Extended thinking capabilities    |

## Capabilities Legend

| Symbol | Meaning                             |
| ------ | ----------------------------------- |
| 🛠️    | Supports tool use                   |
| 📎     | Supports attachments (images, PDFs) |
| 💾     | Supports prompt caching             |
| ⚡      | Supports streaming                  |
| 💡     | Extended reasoning/thinking         |

***

## Anthropic (Claude)

| Model ID            | Name              | Tags                | Context | Capabilities   | Providers                      |
| ------------------- | ----------------- | ------------------- | ------- | -------------- | ------------------------------ |
| `claude-4.5-haiku`  | Claude 4.5 Haiku  | fast, cheap         | 200K    | 🛠️ 📎 💾 ⚡    | anthropic, openrouter, reliant |
| `claude-4.5-opus`   | Claude 4.5 Opus   | flagship, reasoning | 200K    | 🛠️ 📎 💾 ⚡ 💡 | anthropic, openrouter, reliant |
| `claude-4.5-sonnet` | Claude 4.5 Sonnet | moderate, reasoning | 200K    | 🛠️ 📎 💾 ⚡ 💡 | anthropic, openrouter, reliant |
| `claude-4.6-opus`   | Claude 4.6 Opus   | flagship, reasoning | 200K    | 🛠️ 📎 💾 ⚡ 💡 | anthropic, openrouter, reliant |
| `claude-4.6-sonnet` | Claude 4.6 Sonnet | moderate, reasoning | 200K    | 🛠️ 📎 💾 ⚡ 💡 | anthropic, openrouter, reliant |

**Note:** All Claude models support attachments (images, PDFs) and prompt caching.

***

## OpenAI (GPT)

| Model ID              | Name                | Tags                          | Context | Capabilities   | Providers                 |
| --------------------- | ------------------- | ----------------------------- | ------- | -------------- | ------------------------- |
| `gpt-5.2`             | GPT-5.2             | moderate, reasoning           | 400K    | 🛠️ 📎 💾 ⚡ 💡 | openai, openrouter        |
| `gpt-5.2-codex`       | GPT-5.2 Codex       | flagship, reasoning           | 400K    | 🛠️ 📎 💾 ⚡ 💡 | codex, openai, openrouter |
| `gpt-5.2-pro`         | GPT-5.2 Pro         | moderate, reasoning           | 400K    | 🛠️ 📎 💾 ⚡ 💡 | openai, openrouter        |
| `gpt-5.3-codex`       | GPT-5.3 Codex       | flagship, reasoning           | 400K    | 🛠️ 📎 💾 ⚡ 💡 | codex, openai, openrouter |
| `gpt-5.3-codex-spark` | GPT-5.3 Codex Spark | fast, reasoning               | 128K    | 🛠️ 💾 ⚡ 💡    | codex                     |
| `gpt-5.4`             | GPT-5.4             | flagship, moderate, reasoning | 1M      | 🛠️ 📎 💾 ⚡ 💡 | codex, openai, openrouter |
| `gpt-5.4-mini`        | GPT-5.4 Mini        | fast, cheap                   | 400K    | 🛠️ 📎 💾 ⚡ 💡 | codex, openai, openrouter |
| `gpt-5.4-pro`         | GPT-5.4 Pro         | flagship, reasoning           | 1M      | 🛠️ 📎 ⚡ 💡    | openai                    |
| `gpt-5.5`             | GPT-5.5             | flagship, moderate, reasoning | 1M      | 🛠️ 📎 💾 ⚡ 💡 | codex, openai, openrouter |

**Note:** OpenAI's GPT models with varying context windows and capabilities.

***

## Google (Gemini)

| Model ID                             | Name                                  | Tags                | Context | Capabilities   | Providers                   |
| ------------------------------------ | ------------------------------------- | ------------------- | ------- | -------------- | --------------------------- |
| `gemini-2.5-flash`                   | Gemini 2.5 Flash                      | fast, cheap         | 1M      | 🛠️ 📎 ⚡       | gemini, openrouter, reliant |
| `gemini-2.5-flash-lite`              | Gemini 2.5 Flash Lite                 | cheap, fast         | 1M      | 🛠️ 📎 ⚡       | gemini, openrouter, reliant |
| `gemini-2.5-pro`                     | Gemini 2.5 Pro                        | moderate, reasoning | 1M      | 🛠️ 📎 ⚡ 💡    | gemini, openrouter, reliant |
| `gemini-3-flash-preview`             | Gemini 3 Flash Preview                | fast                | 1M      | 🛠️ 📎 ⚡       | gemini, openrouter, reliant |
| `gemini-3-pro-preview`               | Gemini 3 Pro Preview                  | flagship, reasoning | 1M      | 🛠️ 📎 ⚡ 💡    | gemini, openrouter          |
| `gemini-3.1-flash-lite-preview`      | Gemini 3.1 Flash-Lite Preview         | cheap, fast         | 1M      | 🛠️ 📎 ⚡       | gemini                      |
| `gemini-3.1-pro-preview`             | Gemini 3.1 Pro Preview                | flagship, reasoning | 1M      | 🛠️ 📎 💾 ⚡ 💡 | gemini, openrouter, reliant |
| `gemini-3.1-pro-preview-customtools` | Gemini 3.1 Pro Preview (Custom Tools) | reasoning           | 1M      | 🛠️ 📎 💾 ⚡ 💡 | gemini                      |

**Note:** Google's Gemini models with large context windows.

***

## Models by Tag

Find models by capability. Use these tables to answer "what are my options for X?"

### Flagship

*Most capable models for complex tasks*

| Model                    | Provider  | Context | Capabilities   |
| ------------------------ | --------- | ------- | -------------- |
| `claude-4.6-opus`        | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.5-opus`        | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.5`                | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.4`                | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.4-pro`            | OpenAI    | 1M      | 🛠️ 📎 ⚡ 💡    |
| `gpt-5.3-codex`          | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.2-codex`          | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3.1-pro-preview` | Google    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3-pro-preview`   | Google    | 1M      | 🛠️ 📎 ⚡ 💡    |

### Moderate

*Balance of capability and cost*

| Model               | Provider  | Context | Capabilities   |
| ------------------- | --------- | ------- | -------------- |
| `gpt-5.5`           | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.4`           | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.6-sonnet` | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.5-sonnet` | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.2-pro`       | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.2`           | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-2.5-pro`    | Google    | 1M      | 🛠️ 📎 ⚡ 💡    |

### Fast

*Optimized for quick responses*

| Model                           | Provider  | Context | Capabilities   |
| ------------------------------- | --------- | ------- | -------------- |
| `gpt-5.3-codex-spark`           | OpenAI    | 128K    | 🛠️ 💾 ⚡ 💡    |
| `claude-4.5-haiku`              | Anthropic | 200K    | 🛠️ 📎 💾 ⚡    |
| `gpt-5.4-mini`                  | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3-flash-preview`        | Google    | 1M      | 🛠️ 📎 ⚡       |
| `gemini-3.1-flash-lite-preview` | Google    | 1M      | 🛠️ 📎 ⚡       |
| `gemini-2.5-flash`              | Google    | 1M      | 🛠️ 📎 ⚡       |
| `gemini-2.5-flash-lite`         | Google    | 1M      | 🛠️ 📎 ⚡       |

### Cheap

*Low cost per token*

| Model                           | Provider  | Context | Capabilities   |
| ------------------------------- | --------- | ------- | -------------- |
| `claude-4.5-haiku`              | Anthropic | 200K    | 🛠️ 📎 💾 ⚡    |
| `gpt-5.4-mini`                  | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3.1-flash-lite-preview` | Google    | 1M      | 🛠️ 📎 ⚡       |
| `gemini-2.5-flash`              | Google    | 1M      | 🛠️ 📎 ⚡       |
| `gemini-2.5-flash-lite`         | Google    | 1M      | 🛠️ 📎 ⚡       |

### Reasoning

*Extended thinking capabilities*

| Model                                | Provider  | Context | Capabilities   |
| ------------------------------------ | --------- | ------- | -------------- |
| `claude-4.6-opus`                    | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.5-opus`                    | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.5`                            | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.4`                            | OpenAI    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.4-pro`                        | OpenAI    | 1M      | 🛠️ 📎 ⚡ 💡    |
| `gpt-5.3-codex`                      | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.3-codex-spark`                | OpenAI    | 128K    | 🛠️ 💾 ⚡ 💡    |
| `gpt-5.2-codex`                      | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3.1-pro-preview`             | Google    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-3-pro-preview`               | Google    | 1M      | 🛠️ 📎 ⚡ 💡    |
| `gemini-3.1-pro-preview-customtools` | Google    | 1M      | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.6-sonnet`                  | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `claude-4.5-sonnet`                  | Anthropic | 200K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.2-pro`                        | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gpt-5.2`                            | OpenAI    | 400K    | 🛠️ 📎 💾 ⚡ 💡 |
| `gemini-2.5-pro`                     | Google    | 1M      | 🛠️ 📎 ⚡ 💡    |

***

## Using Models

### Tag-Based Selection (Recommended)

Select models by capability tags for provider-agnostic workflows:

```yaml theme={null}
# In presets or workflow nodes
model:
  tags: [flagship]      # Best quality model available
  
model:
  tags: [fast, cheap]   # Prefer fast+cheap, falls back to fast-only or cheap-only

model:
  tags: [local, fast]   # Prefer local, use fast cloud model as fallback
```

### Explicit Model ID

Select a specific model by ID:

```yaml theme={null}
model:
  id: claude-4.5-sonnet
```

### In Workflow Inputs

Workflow inputs use model ID strings (for UI dropdown):

```yaml theme={null}
inputs:
  model:
    type: model
    default: claude-4.5-sonnet  # Model ID string for input default
```

### In Presets

Presets can use tag-based selection:

```yaml theme={null}
name: my-preset
tag: agent
params:
  model:
    tags: [flagship]  # Works with any provider
```

***

## Provider Configuration

Models require the appropriate provider to be configured in Settings → AI:

| Provider  | Models     |
| --------- | ---------- |
| Anthropic | `claude-*` |
| OpenAI    | `gpt-*`    |
| Google    | `gemini-*` |

See [API Keys & Providers](/settings/api-keys) for setup instructions.