Create Completion

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

The name of the model to use.

The prompt to generate completions for. It can be a single string or an array of strings. It can also be an array of integers or an array of integer arrays, which allows to pass already tokenized prompt. If multiple prompts are specified, several choices with corresponding index will be returned in the output."

The list of base64 encoded images for visual language completition generation. They should be formatted as MIME_TYPE,<base64 encoded str> eg. data:image/jpeg;base64,<base64 encoded str> Additionally, the number of images provided should match the number of '<image>' special token in the prompt

The maximum number of tokens to generate in the completion.

If the token count of your prompt plus max_tokens exceed the model's context length, the behavior is depends on context_length_exceeded_behavior. By default, max_tokens will be lowered to fit in the context window instead of returning an error.

Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.

The maximum value for logprobs is 5.

Echo back the prompt in addition to the completion.

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.

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.

Top-k sampling is another sampling method where the k most probable next tokens are filtered and the probability mass is redistributed among only those k next tokens. The value of k controls the number of candidates for the next token at each step during text generation.

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.

Reasonable value is around 0.1 to 1 if the aim is to just reduce repetitive samples somewhat. If the aim is to strongly suppress repetition, then one can increase the coefficients up to 2, but this can noticeably degrade the quality of samples. Negative values can be used to increase the likelihood of repetition.

See also presence_penalty for penalizing tokens that have at least one appearance at a fixed rate.

OpenAI compatible (follows OpenAI's conventions for handling token frequency and repetition penalties).

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.

Reasonable value is around 0.1 to 1 if the aim is to just reduce repetitive samples somewhat. If the aim is to strongly suppress repetition, then one can increase the coefficients up to 2, but this can noticeably degrade the quality of samples. Negative values can be used to increase the likelihood of repetition.

See also frequence_penalty for penalizing tokens at an increasing rate depending on how often they appear.

OpenAI compatible (follows OpenAI's conventions for handling token frequency and repetition penalties).

Applies a penalty to repeated tokens to discourage or encourage repetition. A value of 1.0 means no penalty, allowing free repetition. Values above 1.0 penalize repetition, reducing the likelihood of repeating tokens. Values between 0.0 and 1.0 reward repetition, increasing the chance of repeated tokens. For a good balance, a value of 1.2 is often recommended. Note that the penalty is applied to both the generated output and the prompt in decoder-only models.

Specifies the learning rate for the Mirostat sampling algorithm, which controls how quickly the model adjusts its token distribution to maintain the target perplexity. A smaller value slows down the adjustments, leading to more stable but gradual shifts, while higher values speed up corrections at the cost of potential instability.

Defines the target perplexity for the Mirostat algorithm. Perplexity measures the unpredictability of the generated text, with higher values encouraging more diverse and creative outputs, while lower values prioritize predictability and coherence. The algorithm dynamically adjusts the token selection to maintain this target during text generation.

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

This setting controls whether the model should ignore the End of Sequence (EOS) token. When set to True, the model will continue generating tokens even after the EOS token is produced. By default, it stops when the EOS token is reached.

Up to 4 sequences where the API will stop generating further tokens. The returned text will contain the stop sequence.

Allows to force the model to produce specific output format.

Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

Optional JSON schema can be provided as response_format = {"type": "json_object", "schema": <json_schema>}.

Important: when using JSON mode, it's crucial to also instruct the model to produce JSON via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length. In this case the return value might not be a valid JSON.

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

What to do if the token count of prompt plus max_tokens exceeds the model's context window.

Passing truncate limits the max_tokens to at most context_window_length - prompt_length. This is the default.

Passing error would trigger a request error.

The default of 'truncate' is selected as it allows to ask for high max_tokens value while respecting the context window length without having to do client-side prompt tokenization.

Note, that it differs from OpenAI's behavior that matches that of error.

A unique identifier representing your end-user, which can help monitor and detect abuse

A unique identifier of the response.

The object type, which is always "text_completion".

The Unix time in seconds when the response was generated.

The model used for the completion.

The list of generated completion choices.

Usage statistics.

For streaming responses, usage field is included in the very last response chunk returned.

Note that returning usage for streaming requests is an OpenAI API extension. If you use OpenAI SDK, you might access the field directly even if it's not present in the type signature in the SDK.