Openai Compatible Chat Completions Api

Headers

x-api-key

string | null

Your API key.

Body

application/json

model

string

required

Model ID used to generate the response, like meta/llama-4-scout or moonshotai/kimi-k2-0905. CompileLabs offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Required string length: 3 - 255

messages

(ChatCompletionDeveloperMessageParam · object | ChatCompletionSystemMessageParam · object | ChatCompletionUserMessageParam · object | ChatCompletionToolMessageParam · object | ChatCompletionAssistantMessageParam · object)[]

required

A list of messages comprising the conversation so far.

Minimum array length: 1

ChatCompletionDeveloperMessageParam
ChatCompletionSystemMessageParam
ChatCompletionUserMessageParam
ChatCompletionToolMessageParam
ChatCompletionAssistantMessageParam

Show child attributes

messages.content

required

The contents of the developer message.

Example:

"How can I help you today?"

messages.role

string

default:developer

The role of the messages author, in this case developer.

Allowed value: "developer"

messages.name

string | null

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

Example:

"jane_doe"

stream

boolean | null

default:false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information, along with the streaming responses guide for more information on how to handle the streaming events.

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:

auto,

none,

required

tools

FunctionTool · object[] | null

A list of tools the model may call. Currently, only functions are supported as a tool.

Show child attributes

tools.function

FunctionObject · object

required

The function that the model may call.

Show child attributes

tools.function.name

string

required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Maximum string length: 64

tools.function.parameters

FunctionParameters · object

required

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

Show child attributes

tools.function.parameters.type

string

default:object

Allowed value: "object"

tools.function.parameters.required

string[] | null

which one of the parameter is required

Example:

"location"

tools.function.parameters.properties

Properties · object

A map of property names to their types and descriptions. Each property is an object with 'type' and 'description' fields. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Example:

{
  "location": {
    "description": "The city and state, e.g. San Francisco, CA",
    "type": "string"
  },
  "unit": {
    "description": "Unit for the output - one of (celsius, fahrenheit)",
    "type": "string"
  }
}

tools.function.description

string | null

A description of what the function does, used by the model to choose when and how to call the function.

Maximum string length: 1024

Example:

"Get the current weather in a given location"

tools.type

string

default:function

Allowed value: "function"

parallel_tool_calls

boolean

default:true

Whether to enable parallel function calling.

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.

Required range: x > 1

Example:

1024

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:

0.7

top_p

number | null

default:1

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:

0.9

response_format

Text · object

Setting to { 'type': 'json_schema', 'json_schema': {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Text
JSONSchema

Show child attributes

response_format.type

string

default:text

The type of response format being defined. Always text.

Allowed value: "text"

Example:

{
  "json_schema": {
    "properties": {
      "location": {
        "description": "The city and state, e.g. San Francisco, CA",
        "type": "string"
      },
      "unit": {
        "description": "Unit for the output - one of (celsius, fahrenheit)",
        "type": "string"
      }
    },
    "required": ["location", "unit"],
    "type": "object"
  },
  "type": "json_schema"
}

Response

Successful Response

string

required

A unique identifier for the chat completion.

created

integer

required

The Unix time in seconds when the response was generated.

model

string

required

The model used for the chat completion.

choices

ChatCompletionChoice · object[]

required

The list of chat completion choices.

Show child attributes

choices.index

integer

required

The index of the chat completion choice.

choices.message

ChatCompletionResponseMessage · object

required

The message generated by the model.

Show child attributes

choices.message.role

enum<string>

required

The role of the author of this message.

Available options:

system,

user,

assistant,

developer,

tool

choices.message.content

string | null

The contents of the message.

Example:

"How can I help you today?"

choices.message.tool_calls

ChatCompletionMessageToolCall · object[] | null

The tool calls generated by the model, such as function calls.

Show child attributes

choices.message.tool_calls.id

string

required

The ID of the tool call.

choices.message.tool_calls.function

Function · object

required

The function that the model called.

Show child attributes

choices.message.tool_calls.function.{key}

string

choices.message.tool_calls.type

string

default:function

The type of the tool. Currently, only function is supported.

Allowed value: "function"

Example:

{
  "function": {
    "arguments": "{'location': 'San Francisco'}",
    "name": "get_weather"
  },
  "id": "tool_call_1",
  "type": "function"
}

choices.finish_reason

enum<string>

required

The reason the model stopped generating tokens.

Available options:

stop,

length,

tool_calls,

content_filter

usage

UsageInfo · object

required

Usage statistics for the completion request.

Show child attributes

usage.prompt_tokens

integer

required

The number of tokens in the prompt.

usage.completion_tokens

integer

required

The number of tokens in the generated completion.

usage.total_tokens

integer

required

The total number of tokens used in the request (prompt + completion).

object

string

default:chat.completion

The object type, which is always 'chat.completion'.

Allowed value: "chat.completion"

API reference

Headers

Body

Response