Chat Completion

best_ofinteger nullable

Number of output sequences that are generated from the prompt. From these best_of sequences, the top n sequences are returned. best_of must be greater than or equal to n. This is treated as the beam width when use_beam_search is True. By default, best_of is set to n.

top_kinteger nullable

Controls the number of top tokens to consider. -1 means consider all tokens.

min_pnumber nullable

Float that represents the minimum probability for a token to be considered, relative to the probability of the most likely token. Must be in [0, 1]. Set to 0 to disable this.

use_beam_searchboolean nullable

Whether to use beam search for sampling.

length_penaltynumber nullable

Float that penalizes sequences based on their length. Used in beam search.

repetition_penaltynumber nullable

Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1 encourage the model to use new tokens, while values < 1 encourage the model to repeat tokens.

early_stoppingboolean nullable

Controls the stopping condition for beam search. It accepts the following values: True, where the generation stops as soon as there are best_of complete candidates; False, where an heuristic is applied and the generation stops when is it very unlikely to find better candidates; "never", where the beam search procedure only stops when there cannot be better candidates (canonical beam search algorithm).

stop_token_idsinteger[] nullable

List of tokens that stop the generation when they are generated. The returned output will contain the stop tokens unless the stop tokens are special tokens.

include_stop_str_in_outputboolean nullable

Whether to include the stop strings in output text. Defaults to False.

ignore_eosboolean nullable

Whether to ignore the EOS token and continue generating tokens after the EOS token is generated.

min_tokensinteger nullable

Minimum number of tokens to generate per output sequence before EOS or stop_token_ids can be generated

skip_special_tokensboolean nullable

Whether to skip special tokens in the output. Only supported in vllm.

spaces_between_special_tokensboolean nullable

Whether to add spaces between special tokens in the output. Only supported in vllm.

echoboolean nullable

If true, the new message will be prepended with the last message if they belong to the same role.

add_generation_promptboolean nullable

If true, the generation prompt will be added to the chat template. This is a parameter used by chat template in tokenizer config of the model.

continue_final_messageboolean nullable

If this is set, the chat will be formatted so that the final message in the chat is open-ended, without any EOS tokens. The model will continue this message rather than starting a new one. This allows you to "prefill" part of the model's response for it. Cannot be used at the same time as add_generation_prompt.

add_special_tokensboolean nullable

If true, special tokens (e.g. BOS) will be added to the prompt on top of what is added by the chat template. For most models, the chat template takes care of adding the special tokens so this should be set to false (as is the default).

documentsobject[] nullable

A list of dicts representing documents that will be accessible to the model if it is performing RAG (retrieval-augmented generation). If the template does not support RAG, this argument will have no effect. We recommend that each document should be a dict containing "title" and "text" keys.

chat_templatestring nullable

A Jinja template to use for this conversion. As of transformers v4.44, default chat template is no longer allowed, so you must provide a chat template if the model's tokenizer does not define one and no override template is given

chat_template_kwargsobject nullable

Additional kwargs to pass to the template renderer. Will be accessible by the chat template.

guided_jsonobject nullable

JSON schema for guided decoding. Only supported in vllm.

guided_regexstring nullable

Regex for guided decoding. Only supported in vllm.

guided_choicestring[] nullable

Choices for guided decoding. Only supported in vllm.

guided_grammarstring nullable

Context-free grammar for guided decoding. Only supported in vllm.

guided_decoding_backendstring nullable

If specified, will override the default guided decoding backend of the server for this specific request. If set, must be either 'outlines' / 'lm-format-enforcer'

guided_whitespace_patternstring nullable

If specified, will override the default whitespace pattern for guided json decoding.

priorityinteger nullable

The priority of the request (lower means earlier handling; default: 0). Any priority other than 0 will raise an error if the served model does not use priority scheduling.

metadataMetadata nullable

temperaturenumber nullable

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.

top_pnumber nullable

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.

userstring nullable

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

service_tier'auto' | 'default' | 'flex' nullable

Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:

If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.
If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
If set to 'flex', the request will be processed with the Flex Processing service tier. Learn more.
When not set, the default behavior is 'auto'.

When this parameter is set, the response body will include the service_tier utilized.

modelstring required

ID of the model to use.

modalitiesstring[] nullable

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

reasoning_effort'low' | 'medium' | 'high' nullable

o-series models only

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

max_completion_tokensinteger nullable

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

frequency_penaltynumber nullable

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.

presence_penaltynumber nullable

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.

top_logprobsinteger nullable

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

storeboolean nullable

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

streamboolean nullable

If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

logit_biasobject nullable

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.

logprobsboolean nullable

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

max_tokensinteger nullable

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o-series models.

ninteger nullable

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

seedinteger nullable

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

parallel_tool_callsboolean

Whether to enable parallel function calling during tool use.

v1

Request body

Response