Create Session

curl --request POST \
  --url https://platform.perso.ai/api/v1/session/ \
  --header 'Content-Type: application/json' \
  --header 'PersoPlatform-APIKey: <api-key>' \
  --data '
{
  "prompt": "<string>",
  "capability": [],
  "document": "<string>",
  "llm_type": "<string>",
  "tts_type": "<string>",
  "text_normalization_config": "<string>",
  "text_normalization_locale": "<string>",
  "stt_type": "<string>",
  "stt_text_normalization_config": "<string>",
  "stt_text_normalization_locale": "<string>",
  "model_style": "<string>",
  "agent": "<string>",
  "agent_config": "<string>",
  "interactive_agent_config": "<string>",
  "padding_left": 0,
  "padding_top": 0.5,
  "padding_height": 2.5,
  "background_image": "<string>",
  "extra_data": "<unknown>",
  "mcp_servers": [
    "<string>"
  ]
}
'

import requests

url = "https://platform.perso.ai/api/v1/session/"

payload = {
    "prompt": "<string>",
    "capability": [],
    "document": "<string>",
    "llm_type": "<string>",
    "tts_type": "<string>",
    "text_normalization_config": "<string>",
    "text_normalization_locale": "<string>",
    "stt_type": "<string>",
    "stt_text_normalization_config": "<string>",
    "stt_text_normalization_locale": "<string>",
    "model_style": "<string>",
    "agent": "<string>",
    "agent_config": "<string>",
    "interactive_agent_config": "<string>",
    "padding_left": 0,
    "padding_top": 0.5,
    "padding_height": 2.5,
    "background_image": "<string>",
    "extra_data": "<unknown>",
    "mcp_servers": ["<string>"]
}
headers = {
    "PersoPlatform-APIKey": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'PersoPlatform-APIKey': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: '<string>',
    capability: [],
    document: '<string>',
    llm_type: '<string>',
    tts_type: '<string>',
    text_normalization_config: '<string>',
    text_normalization_locale: '<string>',
    stt_type: '<string>',
    stt_text_normalization_config: '<string>',
    stt_text_normalization_locale: '<string>',
    model_style: '<string>',
    agent: '<string>',
    agent_config: '<string>',
    interactive_agent_config: '<string>',
    padding_left: 0,
    padding_top: 0.5,
    padding_height: 2.5,
    background_image: '<string>',
    extra_data: '<unknown>',
    mcp_servers: ['<string>']
  })
};

fetch('https://platform.perso.ai/api/v1/session/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.perso.ai/api/v1/session/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => '<string>',
    'capability' => [
        
    ],
    'document' => '<string>',
    'llm_type' => '<string>',
    'tts_type' => '<string>',
    'text_normalization_config' => '<string>',
    'text_normalization_locale' => '<string>',
    'stt_type' => '<string>',
    'stt_text_normalization_config' => '<string>',
    'stt_text_normalization_locale' => '<string>',
    'model_style' => '<string>',
    'agent' => '<string>',
    'agent_config' => '<string>',
    'interactive_agent_config' => '<string>',
    'padding_left' => 0,
    'padding_top' => 0.5,
    'padding_height' => 2.5,
    'background_image' => '<string>',
    'extra_data' => '<unknown>',
    'mcp_servers' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "PersoPlatform-APIKey: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.perso.ai/api/v1/session/"

	payload := strings.NewReader("{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("PersoPlatform-APIKey", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.perso.ai/api/v1/session/")
  .header("PersoPlatform-APIKey", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.perso.ai/api/v1/session/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["PersoPlatform-APIKey"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "session_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "status": "CREATED",
  "prompt": "<string>",
  "capability": [
    "LLM"
  ],
  "document": "<string>",
  "llm_type": "<string>",
  "tts_type": "<string>",
  "text_normalization_config": "<string>",
  "text_normalization_locale": "<string>",
  "stt_type": "<string>",
  "stt_text_normalization_config": "<string>",
  "stt_text_normalization_locale": "<string>",
  "model_style": "<string>",
  "agent": "<string>",
  "agent_config": "<string>",
  "interactive_agent_config": "<string>",
  "padding_left": 0,
  "padding_top": 0.5,
  "padding_height": 2.5,
  "background_image": "<string>",
  "extra_data": "<unknown>",
  "mcp_servers": [
    "<string>"
  ]
}

Session Lifecycle

Create Session

Create a new interactive session with the specified capabilities.

Capabilities

Choose one or more capabilities for your session. Each capability has different required fields:

Capability	Description	Required Fields
`STF_WEBRTC`	Full interactive avatar with video streaming	`prompt`, `llm_type`, `model_style`, `tts_type`
`STF_ONPREMISE`	On-premise avatar rendering	`model_style`
`LLM`	Language model conversation only	`prompt`, `llm_type`
`TTS`	Text-to-speech only	`tts_type`
`STT`	Speech-to-text only	`stt_type`

Note: STF_WEBRTC and STF_ONPREMISE cannot be used together.

Note: interactive_agent_config cannot be combined with llm_type or prompt — providing either of them alongside interactive_agent_config is rejected with 400.

Default Behavior

If no capability is specified, the session defaults to STF_WEBRTC.

Example

Select “STF_WEBRTC Session” from the Examples dropdown above to see a complete request example.

POST

api

session

Create Session

curl --request POST \
  --url https://platform.perso.ai/api/v1/session/ \
  --header 'Content-Type: application/json' \
  --header 'PersoPlatform-APIKey: <api-key>' \
  --data '
{
  "prompt": "<string>",
  "capability": [],
  "document": "<string>",
  "llm_type": "<string>",
  "tts_type": "<string>",
  "text_normalization_config": "<string>",
  "text_normalization_locale": "<string>",
  "stt_type": "<string>",
  "stt_text_normalization_config": "<string>",
  "stt_text_normalization_locale": "<string>",
  "model_style": "<string>",
  "agent": "<string>",
  "agent_config": "<string>",
  "interactive_agent_config": "<string>",
  "padding_left": 0,
  "padding_top": 0.5,
  "padding_height": 2.5,
  "background_image": "<string>",
  "extra_data": "<unknown>",
  "mcp_servers": [
    "<string>"
  ]
}
'

import requests

url = "https://platform.perso.ai/api/v1/session/"

payload = {
    "prompt": "<string>",
    "capability": [],
    "document": "<string>",
    "llm_type": "<string>",
    "tts_type": "<string>",
    "text_normalization_config": "<string>",
    "text_normalization_locale": "<string>",
    "stt_type": "<string>",
    "stt_text_normalization_config": "<string>",
    "stt_text_normalization_locale": "<string>",
    "model_style": "<string>",
    "agent": "<string>",
    "agent_config": "<string>",
    "interactive_agent_config": "<string>",
    "padding_left": 0,
    "padding_top": 0.5,
    "padding_height": 2.5,
    "background_image": "<string>",
    "extra_data": "<unknown>",
    "mcp_servers": ["<string>"]
}
headers = {
    "PersoPlatform-APIKey": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'PersoPlatform-APIKey': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: '<string>',
    capability: [],
    document: '<string>',
    llm_type: '<string>',
    tts_type: '<string>',
    text_normalization_config: '<string>',
    text_normalization_locale: '<string>',
    stt_type: '<string>',
    stt_text_normalization_config: '<string>',
    stt_text_normalization_locale: '<string>',
    model_style: '<string>',
    agent: '<string>',
    agent_config: '<string>',
    interactive_agent_config: '<string>',
    padding_left: 0,
    padding_top: 0.5,
    padding_height: 2.5,
    background_image: '<string>',
    extra_data: '<unknown>',
    mcp_servers: ['<string>']
  })
};

fetch('https://platform.perso.ai/api/v1/session/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.perso.ai/api/v1/session/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => '<string>',
    'capability' => [
        
    ],
    'document' => '<string>',
    'llm_type' => '<string>',
    'tts_type' => '<string>',
    'text_normalization_config' => '<string>',
    'text_normalization_locale' => '<string>',
    'stt_type' => '<string>',
    'stt_text_normalization_config' => '<string>',
    'stt_text_normalization_locale' => '<string>',
    'model_style' => '<string>',
    'agent' => '<string>',
    'agent_config' => '<string>',
    'interactive_agent_config' => '<string>',
    'padding_left' => 0,
    'padding_top' => 0.5,
    'padding_height' => 2.5,
    'background_image' => '<string>',
    'extra_data' => '<unknown>',
    'mcp_servers' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "PersoPlatform-APIKey: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.perso.ai/api/v1/session/"

	payload := strings.NewReader("{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("PersoPlatform-APIKey", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.perso.ai/api/v1/session/")
  .header("PersoPlatform-APIKey", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.perso.ai/api/v1/session/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["PersoPlatform-APIKey"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"<string>\",\n  \"capability\": [],\n  \"document\": \"<string>\",\n  \"llm_type\": \"<string>\",\n  \"tts_type\": \"<string>\",\n  \"text_normalization_config\": \"<string>\",\n  \"text_normalization_locale\": \"<string>\",\n  \"stt_type\": \"<string>\",\n  \"stt_text_normalization_config\": \"<string>\",\n  \"stt_text_normalization_locale\": \"<string>\",\n  \"model_style\": \"<string>\",\n  \"agent\": \"<string>\",\n  \"agent_config\": \"<string>\",\n  \"interactive_agent_config\": \"<string>\",\n  \"padding_left\": 0,\n  \"padding_top\": 0.5,\n  \"padding_height\": 2.5,\n  \"background_image\": \"<string>\",\n  \"extra_data\": \"<unknown>\",\n  \"mcp_servers\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "session_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "status": "CREATED",
  "prompt": "<string>",
  "capability": [
    "LLM"
  ],
  "document": "<string>",
  "llm_type": "<string>",
  "tts_type": "<string>",
  "text_normalization_config": "<string>",
  "text_normalization_locale": "<string>",
  "stt_type": "<string>",
  "stt_text_normalization_config": "<string>",
  "stt_text_normalization_locale": "<string>",
  "model_style": "<string>",
  "agent": "<string>",
  "agent_config": "<string>",
  "interactive_agent_config": "<string>",
  "padding_left": 0,
  "padding_top": 0.5,
  "padding_height": 2.5,
  "background_image": "<string>",
  "extra_data": "<unknown>",
  "mcp_servers": [
    "<string>"
  ]
}

Authorizations

PersoPlatform-APIKey

string

header

required

Body

prompt

string | null

Prompt identifier defining the system prompt + intro message. Mutually exclusive with interactive_agent_config.

Minimum string length: 1

capability

enum<string>[]

List of session capabilities to enable (e.g. STF_WEBRTC, STT, LLM).

LLM - LLM
TTS - TTS
STT - STT
STF_ONPREMISE - STF_ONPREMISE
STF_WEBRTC - STF_WEBRTC

Available options:

LLM,

TTS,

STT,

STF_ONPREMISE,

STF_WEBRTC

document

string | null

Optional document identifier to attach as a knowledge source.

Minimum string length: 1

llm_type

string | null

LLM model identifier (use List LLM Types). Mutually exclusive with interactive_agent_config.

Minimum string length: 1

tts_type

string | null

TTS voice/type identifier (use List TTS Types).

Minimum string length: 1

text_normalization_config

string | null

Identifier of the text-normalization config applied to TTS input. Configs bundle regex rulesets that rewrite text before speech synthesis (e.g. 20℉ → 화씨 20도, ₩1,000 → 1,000 원).

Minimum string length: 1

text_normalization_locale

string | null

Locale code (e.g. ko-KR) used to select locale-specific rules from the configured ruleset. If omitted, only locale-agnostic rules run; if set, both locale-agnostic and matching-locale rules run.

Maximum string length: 10

stt_type

string | null

STT engine identifier (use List STT Types). Required only if STT capability is in capability.

Minimum string length: 1

stt_text_normalization_config

string | null

Identifier of the text-normalization config applied to STT output. Same ruleset mechanism as TTS normalization but runs on the transcribed text before it is forwarded to the LLM.

Minimum string length: 1

stt_text_normalization_locale

string | null

Locale code used to select locale-specific rules from the STT normalization config. Behaviour matches text_normalization_locale.

Maximum string length: 10

model_style

string | null

Model style name controlling the avatar's visual style (use List Model Styles).

Minimum string length: 1

agent

string | null

Legacy free-form agent identifier string (deprecated — prefer agent_config).

Maximum string length: 255

agent_config

string | null

Optional agent designer config identifier to drive a tool-using agent.

Minimum string length: 1

interactive_agent_config

string | null

Optional interactive-agent config identifier (pliac-*). When set, llm.request turns run on the external interactive-agent server instead of a single-shot completion. Cannot be combined with llm_type or prompt — providing either alongside is rejected.

Minimum string length: 1

padding_left

number<double> | null

Horizontal avatar position offset, between -1.0 and 1.0. Negative = left, positive = right of frame center.

Required range: -1 <= x <= 1

padding_top

number<double> | null

Vertical avatar position offset from the top, between 0.0 and 1.0 of the frame height.

Required range: 0 <= x <= 1

padding_height

number<double> | null

Avatar height scale multiplier (0-5); 1.0 = unscaled.

Required range: 0 <= x <= 5

background_image

string | null

Optional background image identifier for the avatar scene.

Minimum string length: 1

extra_data

any | null

Free-form JSON payload stored alongside the session for caller-defined metadata.

mcp_servers

string[]

List of MCP server names available to the LLM during the session (use List MCP Types).

Minimum string length: 1

Response

session_id

string

required

read-only

created_at

string<date-time>

required

read-only

status

enum<string>

required

CREATED - Created
EXCHANGED - Exchanged
IN_PROGRESS - In Progress
TERMINATED - Terminated

Available options:

CREATED,

EXCHANGED,

IN_PROGRESS,

TERMINATED

prompt

string | null

Prompt identifier defining the system prompt + intro message. Mutually exclusive with interactive_agent_config.

capability

enum<string>[]

List of session capabilities to enable (e.g. STF_WEBRTC, STT, LLM).

LLM - LLM
TTS - TTS
STT - STT
STF_ONPREMISE - STF_ONPREMISE
STF_WEBRTC - STF_WEBRTC

Available options:

LLM,

TTS,

STT,

STF_ONPREMISE,

STF_WEBRTC

document

string | null

Optional document identifier to attach as a knowledge source.

llm_type

string | null

LLM model identifier (use List LLM Types). Mutually exclusive with interactive_agent_config.

tts_type

string | null

TTS voice/type identifier (use List TTS Types).

text_normalization_config

string | null

text_normalization_locale

string | null

Locale code (e.g. ko-KR) used to select locale-specific rules from the configured ruleset. If omitted, only locale-agnostic rules run; if set, both locale-agnostic and matching-locale rules run.

Maximum string length: 10

stt_type

string | null

STT engine identifier (use List STT Types). Required only if STT capability is in capability.

stt_text_normalization_config

string | null

Identifier of the text-normalization config applied to STT output. Same ruleset mechanism as TTS normalization but runs on the transcribed text before it is forwarded to the LLM.

stt_text_normalization_locale

string | null

Locale code used to select locale-specific rules from the STT normalization config. Behaviour matches text_normalization_locale.

Maximum string length: 10

model_style

string | null

Model style name controlling the avatar's visual style (use List Model Styles).

agent

string | null

Legacy free-form agent identifier string (deprecated — prefer agent_config).

Maximum string length: 255

agent_config

string | null

Optional agent designer config identifier to drive a tool-using agent.

interactive_agent_config

string | null

padding_left

number<double> | null

Horizontal avatar position offset, between -1.0 and 1.0. Negative = left, positive = right of frame center.

Required range: -1 <= x <= 1

padding_top

number<double> | null

Vertical avatar position offset from the top, between 0.0 and 1.0 of the frame height.

Required range: 0 <= x <= 1

padding_height

number<double> | null

Avatar height scale multiplier (0-5); 1.0 = unscaled.

Required range: 0 <= x <= 5

background_image

string | null

Optional background image identifier for the avatar scene.

extra_data

any | null

Free-form JSON payload stored alongside the session for caller-defined metadata.

mcp_servers

string[]

List of MCP server names available to the LLM during the session (use List MCP Types).

Session Resources

Session Lifecycle

Session Operations

Embed

Create Session

Capabilities

Default Behavior

Example

Authorizations

Body

Response