Skip to main content
POST
Creates a model response for the given chat conversation
Choose an exact compatible ID from the model list. Supported parameters and output formats vary by model and connection; this schema does not guarantee every upstream feature. See endpoint availability.

Authorizations

api-key
string
header
required

Your Hicap API key.

Headers

x-hicap-tags
string

One JSON object mapping dimension keys to short string values. Never include secrets or direct personal identifiers. Opaque identity references require approved policy and verified destination handling; see the identity attribution guide.

Body

application/json
model
string
default:gpt-5.2
required

Model ID used to generate the response. See the list of available options

messages
(Developer message · object | System message · object | User message · object | Assistant message · object | Tool message · object | Function message · object)[]
required

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.

Minimum array length: 1

Developer-provided instructions that the model should follow, regardless of messages sent by the user.

temperature
number | null
default:1

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.

Required range: 0 <= x <= 2
Example:

1

top_p
number | null

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.

Required range: 0 <= x <= 1
Example:

1

stream
boolean | null
default:false

Requests an OpenAI-compatible server-sent event stream when supported by the model and connection. Live streaming behavior and content type have not been verified for this documentation update.

stop

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

max_completion_tokens
integer | null

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

presence_penalty
number
default:0

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.

Required range: -2 <= x <= 2
frequency_penalty
number
default:0

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.

Required range: -2 <= x <= 2
logit_bias
object | null

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.

store
boolean | null
default:false

Optional upstream-compatible field. Support and any storage or retention behavior have not been verified for every Hicap model and connection. Do not assume that enabling it stores responses or makes them available for training or evaluation.

metadata
object | null

Optional request metadata. Acceptance, persistence, access, and retrieval are not verified for every model and connection. Do not put secrets or sensitive personal data in this field.

user
string
deprecated

Optional upstream-compatible user reference. Verify support and approved identity handling for your selected model, connection, and destination before sending an identifier.

safety_identifier
string

Optional upstream-compatible safety identifier. Support and destination handling are unverified. Treat opaque or hashed identifiers as potentially personal data; do not send them without an approved policy.

prompt_cache_key
string

Optional upstream-compatible cache key. Acceptance, caching behavior, and retention are model- and backend-dependent and have not been verified for every Hicap connection.

modalities
enum<string>[]

Optional output modalities. Supported values and response formats depend on the selected model and connection; verify before use.

Available options:
text,
audio
audio
object

Optional upstream-compatible audio output settings. Model and connection support, accepted voice identifiers, and output formats have not been verified.

reasoning_effort
enum<string>

Optional upstream-compatible reasoning effort. Supported values and behavior depend on the selected model and backend; verify before use.

Available options:
none,
minimal,
low,
medium,
high,
xhigh
logprobs
boolean | null
default:false

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.

top_logprobs
integer | null

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.

Required range: 0 <= x <= 20
n
integer | null
default:1

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.

Required range: 1 <= x <= 128
Example:

1

prediction
Static Content · object | null

Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

response_format
Text · object

Optional response format. JSON and JSON Schema modes, accepted schemas, and output behavior depend on the selected model and connection. Verify provider acceptance and validate each response; a request field or schema does not guarantee valid or schema-conformant output.

seed
integer | null
deprecated

Optional seed. Support, accepted range, and repeatability depend on the selected model and backend and have not been verified. JavaScript cannot exactly represent all large integers; avoid values outside its safe integer range unless the client and backend support them.

stream_options
object | null

Options for streaming response. Only set this when you set stream: true.

tools
(Function Tool · object | Custom tool · object)[]

A list of tools the model may call. You can provide either custom tools or function tools.

A function tool that can be used to generate a response.

tool_choice

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present.

auto is the default if tools are present.

Available options:
none,
auto,
required
function_call
deprecated

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"name": "my_function"} forces the model to call that function.

none is the default when no functions are present. auto is the default if functions are present.

Available options:
none,
auto
functions
object[]
deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Required array length: 1 - 128 elements
max_tokens
integer | null
deprecated

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.

parallel_tool_calls
boolean | null

Whether to enable parallel function calling during tool use.

prompt_cache_retention
string

Optional upstream-compatible cache retention setting. Support, duration, and actual data handling depend on the selected backend and have not been verified for every Hicap connection.

service_tier
enum<string> | null
default:auto

Optional upstream-compatible service tier. Availability, routing, pricing, and response behavior depend on the selected model and connection and have not been verified for every backend.

Available options:
auto,
default,
flex,
priority
verbosity
enum<string>
default:medium

Optional upstream-compatible verbosity setting. Supported values and behavior depend on the selected model and backend.

Available options:
low,
medium,
high
web_search_options
object

Optional upstream-compatible web search settings. Availability, behavior, and external data handling must be verified for the selected model and connection.

Response

OK

Represents a chat completion response returned by model, based on the provided input.

id
string

A unique identifier for the chat completion.

choices
object[]

A list of chat completion choices. Can be more than one if n is greater than 1.

created
integer

The Unix timestamp (in seconds) of when the chat completion was created.

model
string

The model used for the chat completion.

system_fingerprint
string
deprecated

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

object
enum<string>

The object type, which is always chat.completion.

Available options:
chat.completion
service_tier
enum<string> | null
default:auto

Optional upstream-compatible service tier. Availability, routing, pricing, and response behavior depend on the selected model and connection and have not been verified for every backend.

Available options:
auto,
default,
flex,
priority
usage
object

Usage statistics for the completion request.