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.

Index Signature

[key: string]: number

logprobs?

optional logprobs: ParamOptBool

Defined in: src/client/types.gen.ts:200

max_completion_tokens?

optional max_completion_tokens: ParamOptInt64

Defined in: src/client/types.gen.ts:201

max_tokens?

optional max_tokens: ParamOptInt64

Defined in: src/client/types.gen.ts:202

messages?

optional messages: OpenaiChatCompletionMessageParamUnion[]

Defined in: src/client/types.gen.ts:211

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text , images , and audio .

metadata?

optional metadata: SharedMetadata

Defined in: src/client/types.gen.ts:212

modalities?

optional modalities: string[]

Defined in: src/client/types.gen.ts:227

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"]

Any of “text”, “audio”.

model?

optional model: SharedChatModel

Defined in: src/client/types.gen.ts:228

n?

optional n: ParamOptInt64

Defined in: src/client/types.gen.ts:229

parallel_tool_calls?

optional parallel_tool_calls: ParamOptBool

Defined in: src/client/types.gen.ts:230

portal?

optional portal: LlmapiPortalChatCompletionRequest

Defined in: src/client/types.gen.ts:231

prediction?

optional prediction: OpenaiChatCompletionPredictionContentParam

Defined in: src/client/types.gen.ts:232

presence_penalty?

optional presence_penalty: ParamOptFloat64

Defined in: src/client/types.gen.ts:233

prompt_cache_key?

optional prompt_cache_key: ParamOptString

Defined in: src/client/types.gen.ts:234

reasoning_effort?

optional reasoning_effort: SharedReasoningEffort

Defined in: src/client/types.gen.ts:235

response_format?

optional response_format: OpenaiChatCompletionNewParamsResponseFormatUnion

Defined in: src/client/types.gen.ts:236

safety_identifier?

optional safety_identifier: ParamOptString

Defined in: src/client/types.gen.ts:237

seed?

optional seed: ParamOptInt64

Defined in: src/client/types.gen.ts:238

service_tier?

optional service_tier: OpenaiChatCompletionNewParamsServiceTier

Defined in: src/client/types.gen.ts:239

stop?

optional stop: OpenaiChatCompletionNewParamsStopUnion

Defined in: src/client/types.gen.ts:240

store?

optional store: ParamOptBool

Defined in: src/client/types.gen.ts:241

stream_options?

optional stream_options: OpenaiChatCompletionStreamOptionsParam

Defined in: src/client/types.gen.ts:242

temperature?

optional temperature: ParamOptFloat64

Defined in: src/client/types.gen.ts:243

tool_choice?

optional tool_choice: OpenaiChatCompletionToolChoiceOptionUnionParam

Defined in: src/client/types.gen.ts:244

tools?

optional tools: OpenaiChatCompletionToolParam[]

Defined in: src/client/types.gen.ts:250

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

top_logprobs?

optional top_logprobs: ParamOptInt64

Defined in: src/client/types.gen.ts:251

top_p?

optional top_p: ParamOptFloat64

Defined in: src/client/types.gen.ts:252

user?

optional user: ParamOptString

Defined in: src/client/types.gen.ts:253

web_search_options?

optional web_search_options: OpenaiChatCompletionNewParamsWebSearchOptions

Defined in: src/client/types.gen.ts:254