---
title: Retrieve a session
url: https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/
image: https://developers.wpengine.com/og/docs/ai/api/reference/operations/getsession.png
---

# Retrieve a session

GET

/v1/sessions/{session_id}

Select code sample

```php
<?php


$client = new \GuzzleHttp\Client();


$response = $client->request('GET', 'https://api.ai.wpengine.com/v1/sessions/example', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);


echo $response->getBody();
```

- Current environment

Returns a session with its resolved agent. Accepts a service-token bearer authenticating a site or an API key, either of which must be authorized for the session’s project. Returns 404 if not found or the caller is not authorized.

## Authorizations

- **[bearerAuth](https://developers.wpengine.com/docs/ai/api/reference/#bearerauth)**

## Parameters

### Path Parameters

**session_id**

required

string

The session ID.

## Responses

### 200

The session

Media typeapplication/json

object

**id**

required

string

**type**

required

string

Allowed values: session

**agent**

required

One of:

- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-0-0)
- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-0-1)

object

**id**

required

Unique identifier for the agent.

string

**type**

required

string

Allowed values: agent

**project_id**

required

The project the agent belongs to.

string

**name**

required

string

**model**

required

string

**description**

Free-form description of what the agent does. On an agent with a `profile` this is the profile’s current description.

string

**system_prompt**

User prompt template (site prompt). On an agent with a `profile` this is the profile’s current prompt.

string

**profile**

Server-owned profile the agent follows (see `CreateAgentRequest.profile`). Omitted when the client owns every field.

string

**guardrails**

object

**moderation**

Best-effort custom-agent moderation setting. Product profiles own this value: writes are rejected and the field is omitted from responses for profiled agents.

string

default: disabled

Allowed values: disabled enabled

**managed_fields**

Fields owned by the agent’s profile, which the client cannot write. Omitted when the agent has no profile.

Array\<string>

**allowed_models**

Models the agent’s profile allows as a `model` choice. Omitted when the agent has no profile.

Array\<string>

**temperature**

number format: float

**max_tokens**

Output-token limit per turn (see CreateAgentRequest.max_tokens). Omitted when unset on the agent.

integer

**reasoning_effort**

Catalog-native reasoning effort stored on the agent. Omitted when unset. Allowed values follow the agent’s current model on GET /v1/models.

string

**scopes**

Permission scopes the agent operates under (round-trips the request value).

Array\<string>

**settings**

Feature toggles for the agent (round-trips the request value).

object

**_key_**

additional properties

any

**mcp_servers**

Array\<object>

object

**_key_**

additional properties

any

**tools**

Tool declarations (client tools, knowledge_base grounding entries, and echo/random_number evaluation tool opt-ins) round-tripped from the request.

Array

One of: discriminator: type

- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-1-0)
- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-1-1)
- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-1-2)
- [object](https://developers.wpengine.com/docs/ai/api/reference/operations/getsession/#tab-panel-1-3)

object

**type**

Discriminator for the tools\[] union. Omit for a plain client tool (the default); `custom` is the only value this schema accepts.

string

Allowed values: custom

**name**

Unique tool name. Must be unique within the agent’s `tools` array (across every entry, regardless of type). Always present for tools created since name validation was added; may be absent on an agent whose tools were stored before that validation existed.

string

<= 64 characters /^\[a-zA-Z0-9\_-]{1,64}$/

**description**

Human-readable description of what the tool does.

string

**input_schema**

JSON Schema defining the tool’s input parameters.

object

**label**

Optional short human-readable name for the tool, used alongside `name` and `description` when the gateway matches a search query against deferred tools. Supply it when the tool’s `name` is a slug whose wording a natural-language query would not contain.

string

<= 64 characters

**defer_loading**

When true, the tool is declared but kept out of the model’s tool list until it is needed, so a large catalogue costs no context up front. The gateway offers the agent a search over the deferred tools and loads the matches, and a deferred tool the model names directly is loaded on demand. Once loaded, its input is enforced strictly against its schema — unlike a non-deferred tool, which keeps today’s lenient handling — so a malformed call is rejected with a model-readable error instead of failing downstream. Leave false (the default) for tools that must be callable from the first turn.

boolean

**skills**

Array\<object>

object

**_key_**

additional properties

any

**metadata**

User-supplied string metadata. Reserved keys (“scopes”, “settings”) are surfaced on their own top-level fields rather than appearing here.

object

**_key_**

additional properties

string

<= 512 characters

**created_at**

required

string format: date-time

**updated_at**

string format: date-time

nullable

**status**

required

string

Allowed values: idle running rescheduling terminated error

**title**

string

**reasoning_effort**

Session override for reasoning effort. Omitted when unset (the session inherits the agent’s value, then the provider default).

string

**metadata**

object

**_key_**

additional properties

string

**usage**

required

object

**input_tokens**

required

integer

**output_tokens**

required

integer

**cache_read_input_tokens**

required

integer

**cache_creation_input_tokens**

required

integer

**credits_nano**

required

Cumulative billing total in nano-credits (billionths of a credit)

integer

**archived_at**

string format: date-time

nullable

**created_at**

required

string format: date-time

**updated_at**

string format: date-time

nullable

**owner_id**

Opaque per-visitor id recorded at creation, when the creator supplied one, or the `wpe:` owner id of the person who created a private session. Absent for sessions created without an owner.

string

**site_ids**

Sites this session may work on, sorted. Empty when every site in the project is allowed.

Array\<string>

**model**

The session’s model override, or null when it has none. An override that is no longer servable, or that the agent’s profile no longer allows, is cleared on the session’s next run. Always null on a session that pins its configuration through the v2 session endpoints. Interim; see CreateSessionRequest.model.

string

nullable

**knowledge_bases**

The session’s knowledge-base override. null inherits the agent’s knowledge_base tools; an empty array is ungrounded. Always null on a session that pins its configuration through the v2 session endpoints. Interim; see CreateSessionRequest.knowledge_bases.

Array\<object>

nullable

A knowledge-base grounding entry, shaped like a knowledge_base entry in an agent’s tools. Unknown keys, in the entry or its filters, are rejected with 400.

object

**type**

required

string

Allowed values: knowledge_base

**collection_id**

required

A collection in the agent’s project.

string

**filters**

Filters applied alongside the query.

object

**type**

Post types to include.

Array\<string>

**uri**

Document URIs to include.

Array\<string>

**language**

ISO 639-1 language codes to include.

Array\<string>

**metadata**

Exact-match filters keyed by metadata field; each field maps to a list of accepted values.

object

**_key_**

additional properties

Array\<string>

**created_at**

Inclusive date bounds (RFC-3339). Either bound may be omitted.

object

**gte**

string format: date-time

**lte**

string format: date-time

**modified_at**

Inclusive date bounds (RFC-3339). Either bound may be omitted.

object

**gte**

string format: date-time

**lte**

string format: date-time

#### Example

```json
{
  "type": "session",
  "agent": {
    "type": "agent",
    "guardrails": {
      "moderation": "disabled"
    },
    "managed_fields": [
      "model",
      "system_prompt",
      "description"
    ],
    "tools": [
      {
        "type": "custom",
        "defer_loading": false
      }
    ]
  },
  "status": "idle",
  "knowledge_bases": [
    {
      "type": "knowledge_base",
      "filters": {
        "metadata": {
          "status": [
            "publish"
          ],
          "category": [
            "news",
            "guides"
          ]
        }
      }
    }
  ]
}
```

### 400

Invalid request body or parameters. On agent create and update, error type “profile_unavailable” means the requested profile is not available to the caller.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 401

Missing or invalid bearer token

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

#### Headers

**WWW-Authenticate**

string

##### Example

```
Bearer realm="ai-services"
```

### 403

The token is valid, but the request is forbidden. Error type “permission_error” means the token’s scope/permission is insufficient or the authenticated user is not authorized for the target account; “entitlement_required” means the account may not use WP Engine AI, with error_code giving why when known (not_eligible, terms_required, not_enabled or suspended) and portal_url where to fix it; “account_required” means no billing account could be resolved; and “billing_account_pending” means billing isn’t set up for the account yet, usually because its setup after AI was turned on hasn’t finished. Retry shortly. On /v1/chat/completions when content moderation is enabled, and on /v1/sessions/{session_id}/events, error type “content_policy_violation” instead means the request content was blocked by content moderation policy; that response never identifies which filter or category matched.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 404

The requested resource was not found

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 500

The server encountered an unexpected error while handling the request. Safe to retry once; if it persists, the cause is server-side and the request payload was not the problem.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 503

A required dependency is temporarily unavailable. Retry after a short delay with exponential back-off. An entitlement lookup failure uses error type “entitlement_unavailable”. A model without complete rate coverage uses error type “model_unpriced”. A credit balance that can’t be read uses error type “balance_unavailable”.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

## Was this helpful?

Thanks for the feedback!

```json
{"@context":"https://schema.org","@graph":[{"@type":"WebSite","@id":"https://developers.wpengine.com/#website","name":"WP Engine Product Documentation","url":"https://developers.wpengine.com/","description":"Resources for developing, deploying, and scaling on WP Engine.","inLanguage":"en-US","keywords":["API documentation","product documentation","headless WordPress","managed WordPress hosting"],"publisher":{"@id":"https://wpengine.com/#organization"}}]}
```