Create Agent - Cekura

Authorizations

X-CEKURA-API-KEY

string

header

required

API Key Authentication. It should be included in the header of each request.

Body

Mixin for parsing restql query from request.

NOTE: We are using request.GET instead of request.query_params because this might be called before DRF request is created(i.e from dispatch). This means request.query_params might not be available when this mixin is used.

agent_name

string

required

A descriptive name for your agent

Maximum length: 255

contact_number

string

required

Phone number assigned to this agent for calls (must start with + followed by digits, min 8 chars)

Maximum length: 15

inbound

boolean

required

Specifies if this agent handles inbound calls. Set to true for inbound, false for outbound calls

description

string

required

A detailed description of what this agent does and how it should interact

integer

Unique identifier for the AI agent

project

integer

The project this agent belongs to

organization

integer

The organization this agent belongs to

language

enum<string>

default:en

The primary language this agent uses for communication (e.g. 'en' for English)

ar - Arabic
bg - Bulgarian
zh - Chinese Simplified
cs - Czech
da - Danish
nl - Dutch
en - English
fi - Finnish
fr - French
de - German
el - Greek
hi - Hindi
hu - Hungarian
id - Indonesian
it - Italian
ja - Japanese
ko - Korean
ms - Malay
multi - Multilingual
no - Norwegian
pl - Polish
pt - Portuguese
ro - Romanian
ru - Russian
sk - Slovak
es - Spanish
sv - Swedish
tr - Turkish
uk - Ukrainian
vi - Vietnamese

Available options:

ar,

bg,

zh,

cs,

da,

nl,

en,

fi,

fr,

de,

el,

hi,

hu,

id,

it,

ja,

ko,

ms,

multi,

no,

pl,

pt,

ro,

ru,

sk,

es,

sv,

tr,

uk,

vi

assistant_id

string | null

External assistant service identifier (minimum 10 characters)

Maximum length: 255

chat_assistant_id

string

Chat-specific assistant service identifier (minimum 10 characters)

Maximum length: 255

websocket_url

string

WebSocket endpoint URL for real-time communication (must use ws:// or wss://)

websocket_headers

object

Headers to be sent to the websocket server

Show child attributes

llm_system_prompt

string

System prompt that defines the agent's behavior and personality

llm_model

enum<string>

default:gpt-4o

The LLM model to use for simulating user responses

gpt-4o - gpt-4o
gpt-4o-mini - gpt-4o-mini
gpt-4.1 - gpt-4.1
gpt-4.1-mini - gpt-4.1-mini
claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20240620

Available options:

gpt-4o,

gpt-4o-mini,

gpt-4.1,

gpt-4.1-mini,

claude-3-5-sonnet-20240620

llm_temperature

number

default:0

Controls randomness in responses (0.0-2.0, lower = more focused)

llm_max_tokens

integer

default:4096

Maximum length of simulated responses in tokens

predefined_metrics

any

predefined metrics to use for the agent

transcript_provider

enum<string>

default:vocera

Service provider for speech-to-text transcription

vapi - Vapi
retell - Retell
vocera - Vocera
synthflow - Synthflow
elevenlabs - Elevenlabs
bland - Bland
custom - Custom

Available options:

vapi,

retell,

vocera,

synthflow,

elevenlabs,

bland,

custom

assistant_provider

enum<string>

default:self_hosted

Service provider for the AI assistant functionality

vapi - Vapi
retell - Retell
elevenlabs - Elevenlabs
vocera - Vocera
self_hosted - Self Hosted

Available options:

vapi,

retell,

elevenlabs,

vocera,

self_hosted

vapi_api_key

string

API key for VAPI service provider

retell_api_key

string

API key for Retell service provider

elevenlabs_api_key

string

API key for ElevenLabs voice synthesis service

bland_api_key

string

API key for Bland service provider

custom_provider_api_key

string

API key for custom service provider

custom_provider_data

string

Additional configuration data for custom service provider

synthflow_api_key

string

API key for Synthflow service provider

enabled_personalities

integer[]

Personality profiles enabled for this agent

Response

201 - application/json

Mixin for parsing restql query from request.

agent_name

string

required

A descriptive name for your agent

Maximum length: 255

contact_number

string

required

Phone number assigned to this agent for calls (must start with + followed by digits, min 8 chars)

Maximum length: 15

inbound

boolean

required

Specifies if this agent handles inbound calls. Set to true for inbound, false for outbound calls

description

string

required

A detailed description of what this agent does and how it should interact

knowledge_base_files

string

required

List of knowledge base files attached to the agent

created_at

string<date-time>

required

Timestamp when the agent was created

updated_at

string<date-time>

required

Timestamp when the agent was last updated

integer

Unique identifier for the AI agent

project

integer

The project this agent belongs to

language

enum<string>

default:en

The primary language this agent uses for communication (e.g. 'en' for English)

ar - Arabic
bg - Bulgarian
zh - Chinese Simplified
cs - Czech
da - Danish
nl - Dutch
en - English
fi - Finnish
fr - French
de - German
el - Greek
hi - Hindi
hu - Hungarian
id - Indonesian
it - Italian
ja - Japanese
ko - Korean
ms - Malay
multi - Multilingual
no - Norwegian
pl - Polish
pt - Portuguese
ro - Romanian
ru - Russian
sk - Slovak
es - Spanish
sv - Swedish
tr - Turkish
uk - Ukrainian
vi - Vietnamese

Available options:

ar,

bg,

zh,

cs,

da,

nl,

en,

fi,

fr,

de,

el,

hi,

hu,

id,

it,

ja,

ko,

ms,

multi,

no,

pl,

pt,

ro,

ru,

sk,

es,

sv,

tr,

uk,

vi

assistant_id

string | null

External assistant service identifier (minimum 10 characters)

Maximum length: 255

chat_assistant_id

string

Chat-specific assistant service identifier (minimum 10 characters)

Maximum length: 255

websocket_url

string

WebSocket endpoint URL for real-time communication (must use ws:// or wss://)

websocket_headers

object

Headers to be sent to the websocket server

Show child attributes

llm_system_prompt

string

System prompt that defines the agent's behavior and personality

llm_model

enum<string>

default:gpt-4o

The LLM model to use for simulating user responses

gpt-4o - gpt-4o
gpt-4o-mini - gpt-4o-mini
gpt-4.1 - gpt-4.1
gpt-4.1-mini - gpt-4.1-mini
claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20240620

Available options:

gpt-4o,

gpt-4o-mini,

gpt-4.1,

gpt-4.1-mini,

claude-3-5-sonnet-20240620

llm_temperature

number

default:0

Controls randomness in responses (0.0-2.0, lower = more focused)

llm_max_tokens

integer

default:4096

Maximum length of simulated responses in tokens

transcript_provider

enum<string>

default:vocera

Service provider for speech-to-text transcription

vapi - Vapi
retell - Retell
vocera - Vocera
synthflow - Synthflow
elevenlabs - Elevenlabs
bland - Bland
custom - Custom

Available options:

vapi,

retell,

vocera,

synthflow,

elevenlabs,

bland,

custom

assistant_provider

enum<string>

default:self_hosted

Service provider for the AI assistant functionality

vapi - Vapi
retell - Retell
elevenlabs - Elevenlabs
vocera - Vocera
self_hosted - Self Hosted

Available options:

vapi,

retell,

elevenlabs,

vocera,

self_hosted

vapi_api_key

string

API key for VAPI service provider

retell_api_key

string

API key for Retell service provider

elevenlabs_api_key

string

API key for ElevenLabs voice synthesis service

bland_api_key

string

API key for Bland service provider

custom_provider_api_key

string

API key for custom service provider

custom_provider_data

string

Additional configuration data for custom service provider

synthflow_api_key

string

API key for Synthflow service provider

enabled_personalities

integer[]

Personality profiles enabled for this agent

API Reference

Authorizations

Body

Response