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

# Server Tools

> Let models call Phaseo-operated tools during a request.

Server tools are tools that Phaseo runs for you during a model request. The model decides when to call them, Phaseo executes the tool server-side, and the tool result is fed back into the model loop.

Use server tools when the model needs current time, web context, fetched page text, or a second model's advice without adding your own tool executor.

<Note>
  Server tools are in beta. Request shapes and result payloads may evolve as provider support changes.
</Note>

## Available tools

| Tool             | Type                      | Use it for                                              |
| ---------------- | ------------------------- | ------------------------------------------------------- |
| Datetime         | `gateway:datetime`        | Current date and time in up to 5 timezones              |
| Web Search       | `phaseo:web_search`       | Model-directed web searches during a request            |
| Web Fetch        | `phaseo:web_fetch`        | Fetching and extracting text from specific URLs         |
| Advisor          | `phaseo:advisor`          | Consulting another model mid-generation                 |
| Subagent         | `phaseo:subagent`         | Delegating focused work to a worker model               |
| Fusion           | Advisor workflow          | Consulting several advisor models and an optional judge |
| Image Generation | `phaseo:image_generation` | Creating images from the model tool loop                |

## How server tools work

1. Add one or more server tools to the `tools` array.
2. The model decides whether it needs a tool and emits a tool call.
3. Phaseo intercepts the server-tool call, executes it, and sends the result back to the model.
4. The model continues and writes the final response.

Server tools can be used alongside your own function tools. Phaseo executes only the server tools; your application still handles regular `function` tool calls.

## Quick start

```bash theme={null}
curl https://api.phaseo.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "messages": [
      { "role": "user", "content": "What are the latest AI policy updates this week?" }
    ],
    "tools": [
      { "type": "phaseo:web_search" },
      { "type": "gateway:datetime", "parameters": { "timezones": ["Europe/London", "UTC"] } }
    ]
  }'
```

## Combining with function tools

```json theme={null}
{
  "model": "openai/gpt-5-nano",
  "messages": [
    { "role": "user", "content": "Find recent funding news and save the best item." }
  ],
  "tools": [
    { "type": "phaseo:web_search", "parameters": { "max_results": 3 } },
    {
      "type": "function",
      "function": {
        "name": "save_research_item",
        "description": "Save a selected research item",
        "parameters": {
          "type": "object",
          "properties": {
            "title": { "type": "string" },
            "url": { "type": "string" }
          },
          "required": ["title", "url"]
        }
      }
    }
  ]
}
```

If the model calls `phaseo:web_search`, Phaseo executes that call automatically. If it calls `save_research_item`, your application receives the function call and must return the function result in a follow-up request.

## Supported endpoints

Server tools are supported on:

* `/v1/chat/completions`
* `/v1/responses`
* `/v1/messages`

Streaming requests are supported. For gateway-managed server tools, Phaseo may materialize the upstream tool-call turn, execute the server tool, continue the loop, and emit a synthetic stream for the final response.

## Usage tracking

Server-tool usage is reported in `usage.server_tool_use`:

```json theme={null}
{
  "usage": {
    "input_tokens": 105,
    "output_tokens": 250,
    "server_tool_use": {
      "datetime_requests": 1,
      "web_search_requests": 2,
      "web_search_results": 8,
      "web_fetch_requests": 1,
      "advisor_requests": 1,
      "subagent_requests": 1,
      "image_generation_requests": 1
    }
  }
}
```

Pricing can also use server-tool meters such as `server_tool_web_search_requests`, `server_tool_web_search_extra_results`, `server_tool_web_fetch_requests`, `server_tool_advisor_requests`, `server_tool_image_generation_requests`, `native_web_search_requests`, and `native_web_fetch_requests` when configured on model price cards.

## Tool pages

<Columns cols={2}>
  <Card title="Datetime" icon="clock" href="./datetime">
    Give the model the current date and time.
  </Card>

  <Card title="Web Search" icon="search" href="./web-search">
    Let the model search the web when it needs current information.
  </Card>

  <Card title="Web Fetch" icon="file-search" href="./web-fetch">
    Let the model fetch and read specific URLs.
  </Card>

  <Card title="Advisor" icon="message-square" href="./advisor">
    Let one model consult another model for guidance mid-generation.
  </Card>

  <Card title="Subagent" icon="cpu" href="./subagent">
    Let the model delegate focused tasks to a worker model.
  </Card>

  <Card title="Fusion" icon="sparkles" href="./fusion">
    Let the Playground configure several advisor models for one answer.
  </Card>

  <Card title="Image Generation" icon="image" href="./image-generation">
    Let the model create images while answering.
  </Card>
</Columns>