[chatgpt](../readme.md) / [Exports](../modules.md) / [openai](../modules/openai.md) / CreateChatCompletionRequest # Interface: CreateChatCompletionRequest [openai](../modules/openai.md).CreateChatCompletionRequest **`Export`** **`Interface`** CreateChatCompletionRequest ## Table of contents ### Properties - [frequency\_penalty](openai.CreateChatCompletionRequest.md#frequency_penalty) - [logit\_bias](openai.CreateChatCompletionRequest.md#logit_bias) - [max\_tokens](openai.CreateChatCompletionRequest.md#max_tokens) - [messages](openai.CreateChatCompletionRequest.md#messages) - [model](openai.CreateChatCompletionRequest.md#model) - [n](openai.CreateChatCompletionRequest.md#n) - [presence\_penalty](openai.CreateChatCompletionRequest.md#presence_penalty) - [stop](openai.CreateChatCompletionRequest.md#stop) - [stream](openai.CreateChatCompletionRequest.md#stream) - [temperature](openai.CreateChatCompletionRequest.md#temperature) - [top\_p](openai.CreateChatCompletionRequest.md#top_p) - [user](openai.CreateChatCompletionRequest.md#user) ## Properties ### frequency\_penalty • `Optional` **frequency\_penalty**: `number` Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model\'s likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details) **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:314](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L314) ___ ### logit\_bias • `Optional` **logit\_bias**: `object` Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:320](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L320) ___ ### max\_tokens • `Optional` **max\_tokens**: `number` The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens). **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:302](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L302) ___ ### messages • **messages**: [`ChatCompletionRequestMessage`](openai.ChatCompletionRequestMessage.md)[] The messages to generate chat completions for, in the [chat format](/docs/guides/chat/introduction). **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:266](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L266) ___ ### model • **model**: `string` ID of the model to use. Currently, only `gpt-3.5-turbo` and `gpt-3.5-turbo-0301` are supported. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:260](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L260) ___ ### n • `Optional` **n**: `number` How many chat completion choices to generate for each input message. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:284](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L284) ___ ### presence\_penalty • `Optional` **presence\_penalty**: `number` Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model\'s likelihood to talk about new topics. [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details) **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:308](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L308) ___ ### stop • `Optional` **stop**: [`CreateChatCompletionRequestStop`](../modules/openai.md#createchatcompletionrequeststop) **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:296](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L296) ___ ### stream • `Optional` **stream**: `boolean` If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:290](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L290) ___ ### temperature • `Optional` **temperature**: `number` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:272](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L272) ___ ### top\_p • `Optional` **top\_p**: `number` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:278](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L278) ___ ### user • `Optional` **user**: `string` A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). **`Memberof`** CreateChatCompletionRequest #### Defined in [src/types.ts:326](https://github.com/transitive-bullshit/chatgpt-api/blob/48cb944/src/types.ts#L326)