POST /api/internal/chat/completions — prem-studio-api

Chat

Create a chat completion (OpenAI compatible).

post/api/internal/chat/completions

Request body

modelstring required

The identifier of the model to use for generating completions. This can be a model ID or an alias.

frequency_penaltynumber

A value between -2.0 and 2.0 that penalizes new tokens based on their frequency in the text so far. Higher values decrease the likelihood of the model repeating the same tokens.

max_completion_tokensinteger nullable

The maximum number of tokens to generate in the completion. If null, will use the model's maximum context length. This is the maximum number of tokens that will be generated.

presence_penaltynumber

A value between -2.0 and 2.0 that penalizes new tokens based on whether they appear in the text so far. Higher values increase the likelihood of the model talking about new topics.

seedinteger

A seed value for deterministic sampling. Using the same seed with the same parameters will generate the same completion.

streamboolean

If true, partial message deltas will be sent as server-sent events. Useful for showing progressive generation in real-time.

temperaturenumber nullable

Controls randomness in the model's output. Values between 0 and 2. Lower values make the output more focused and deterministic, higher values make it more random and creative.

top_pnumber nullable

An alternative to temperature for controlling randomness. Controls the cumulative probability of tokens to consider. Lower values make output more focused.

Response

chat completion response

idstring required

A unique identifier for this chat completion response. Can be used for tracking or debugging.

createdinteger required

The Unix timestamp (in seconds) indicating when this completion was generated by the API.

modelstring required

The specific model used to generate this completion. This will be the model's full identifier string.

system_fingerprintstring nullable

A unique identifier for the system state that generated this response. Useful for tracking model behavior across requests.

object'chat.completion' required

The type of object returned, always "chat.completion" for chat completion responses.

Changes

Changed in 7 of the 19 revisions of this API.13637

Sep 6, 2025872932ae0b8a1See the full diff
- ○
  the response_format request property default value {"type":"text","json_schema":{}} was removed
  request-property-default-value-removed
Sep 4, 20256fce808cc14e9510See the full diff
- ▲
  removed subschema #1 subschema #2 from the tool_choice request property anyOf list
  request-property-any-of-removed
- ▲
  request property messages/items/tool_calls/items/type was restricted to a list of enum values
  request-property-became-enum
- ▲
  the response property choices/items/logprobs became nullable for the status 200 (media type: text/event-stream)
  response-property-became-nullable
- ▲
  the response property choices/items/message/content became nullable for the status 200 (media type: application/json)
  response-property-became-nullable
- ▲
  the response property system_fingerprint became nullable for the status 200 (media type: application/json)
  response-property-became-nullable
- ▲
  the object response property const value chat.completion was removed for the status 200 (media type: application/json)
  response-property-const-removed
- ▲
  the object response property const value chat.completion.chunk was removed for the status 200 (media type: text/event-stream)
  response-property-const-removed
- ▲
  the type response property const value function was removed for the status 200 (media type: application/json)
  response-property-const-removed
- ▲
  the type response property const value function was removed for the status 200 (media type: text/event-stream)
  response-property-const-removed
- ●
  the max_completion_tokens request property's min was set to 0.00
  request-property-min-set
- ●
  added the new chat.completion enum value to the object response property for the response status 200 (media type: application/json)
  response-property-enum-value-added
- ●
  added the new chat.completion.chunk enum value to the object response property for the response status 200 (media type: text/event-stream)
  response-property-enum-value-added
- ●
  added the new function enum value to the choices/items/delta/tool_calls/items/type response property for the response status 200 (media type: text/event-stream)
  response-property-enum-value-added
- ●
  added the new function enum value to the choices/items/message/tool_calls/items/type response property for the response status 200 (media type: application/json)
  response-property-enum-value-added
- ○
  added subschema #1 subschema #2 to the tool_choice request property anyOf list
  request-property-any-of-added
- ○
  the request property max_completion_tokens became nullable
  request-property-became-nullable
- ○
  the request property messages/items/content became nullable
  request-property-became-nullable
- ○
  the request property response_format/json_schema/additionalProperties/ became nullable
  request-property-became-nullable
- ○
  the request property temperature became nullable
  request-property-became-nullable
- ○
  the request property tools/items/ became nullable
  request-property-became-nullable
- ○
  the request property top_p became nullable
  request-property-became-nullable
- ○
  the type request property const value function was removed
  request-property-const-removed
- ○
  added the new function enum value to the request property messages/items/tool_calls/items/type
  request-property-enum-value-added
- ○
  the max_completion_tokens request property's exclusiveMinimum was decreased from 0.00 to true
  request-property-exclusive-min-decreased
Aug 21, 20253eac827d87b913See the full diff
- ●
  added the new tool enum value to the choices/items/message/role response property for the response status 200
  response-property-enum-value-added
- ○
  added the optional property choices/items/message/name to the response with the 200 status
  response-optional-property-added
- ○
  added the optional property choices/items/message/tool_call_id to the response with the 200 status
  response-optional-property-added
- ○
  added the optional property choices/items/message/tool_calls to the response with the 200 status
  response-optional-property-added
Aug 20, 20254ba54de0b7076See the full diff
- ○
  added the new optional request property messages/items/name
  new-optional-request-property
- ○
  added the new optional request property messages/items/tool_call_id
  new-optional-request-property
- ○
  added the new optional request property messages/items/tool_calls
  new-optional-request-property
- ○
  the request property messages/items/content became nullable
  request-property-became-nullable
- ○
  the request property messages/items/content became optional
  request-property-became-optional
- ○
  added the new tool enum value to the request property messages/items/role
  request-property-enum-value-added
Jul 30, 20256251de8da20038See the full diff
- ▲
  the request property messages/items/content became not nullable
  request-property-became-not-nullable
- ▲
  the request property messages/items/content became required
  request-property-became-required
- ▲
  the messages/items/content request property type/format changed from null/ to string/
  request-property-type-changed
- ○
  added the optional property service_tier to the response with the 200 status
  response-optional-property-added
- ○
  added the optional property system_fingerprint to the response with the 200 status
  response-optional-property-added
- ○
  added the optional property usage to the response with the 200 status
  response-optional-property-added
- ○
  added the required property choices to the response with the 200 status
  response-required-property-added
- ○
  added the required property created to the response with the 200 status
  response-required-property-added
- ○
  added the required property id to the response with the 200 status
  response-required-property-added
- ○
  added the required property model to the response with the 200 status
  response-required-property-added
- ○
  added the required property object to the response with the 200 status
  response-required-property-added
Jul 1, 20255dacf54bc4d22See the full diff
- ○
  added the new optional request property tool_choice
  new-optional-request-property
- ○
  added the new optional request property tools
  new-optional-request-property
May 27, 202570f7bad608d617See the full diff
- ▲
  removed the enum value tool of the request property messages/items/role
  request-property-enum-value-removed
- ○
  the request property frequency_penalty became optional
  request-property-became-optional
- ○
  the request property max_completion_tokens became optional
  request-property-became-optional
- ○
  the request property presence_penalty became optional
  request-property-became-optional
- ○
  the request property stream became optional
  request-property-became-optional
- ○
  the request property temperature became optional
  request-property-became-optional
- ○
  the request property top_p became optional
  request-property-became-optional
- ○
  the response_format request property default value {"type":"text","json_schema":{}} was added
  request-property-default-value-added

Full history