Create Chat Completion (Streaming)

POST: https://www.kkiai.com/v1/chat/completions

Given a list of messages, the model returns one or more predicted completions, and streams the response incrementally.

Create a completion for the provided messages and parameters.

Official documentation: https://docs.anthropic.com/en/docs/build-with-claude/streaming#basic-streaming-request

Request Parameters

Authorization

Add the Authorization parameter to the Header, with its value being the Token concatenated after Bearer.

Example: Authorization: Bearer YOUR_API_KEY

Header Parameters

Parameter Name	Type	Required	Description	Example
Content-Type	string	Required	Request content type.	application/json
Accept	string	Required	Response content type.	application/json
Authorization	string	Required	API key used for authentication.	Bearer YOUR_API_KEY

Body Parameters (application/json)

Parameter Name	Type	Required	Description
model	string	Required	The ID of the model to use. For details on which models are compatible with the Chat API, see the model endpoint compatibility table.
messages	array[object]	Required	A list of messages comprising the conversation so far.
└ role	string	Required	The role of the message author, such as system, user, or assistant.
└ content	string	Required	The text content of the message.
temperature	number	Optional	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_p	number	Optional	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. We generally recommend altering this or temperature, but not both.
n	integer	Optional	Defaults to 1. How many chat completion choices to generate for each input message.
stream	boolean	Required	Set this to true to receive partial message deltas as data-only server-sent events. The stream is terminated by a data: [DONE] message.
stop	string or array	Optional	Defaults to null. Up to 4 sequences where the API will stop generating further tokens.
max_tokens	integer	Optional	Defaults to inf. The maximum number of tokens to generate in the chat completion.
presence_penalty	number	Optional	Defaults to 0. A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
frequency_penalty	number	Optional	Defaults to 0. A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
logit_bias	object or null	Optional	Modifies the likelihood of specified tokens appearing in the completion.
user	string	Optional	A unique identifier representing your end user, which can help monitor and detect abuse.
response_format	object	Optional	An object specifying the format that the model must output.
seed	integer	Optional	If specified, the system will make a best effort to sample deterministically.
tools	array[object]	Optional	A list of tools the model may call. Currently, only functions are supported as a tool.
tool_choice	string or object	Optional	Controls which function, if any, the model calls.

Request Example

{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}

cURL Example

curl --location --request POST 'https://www.kkiai.com/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Response

🟢 200 OK

Response Body

Parameter Name	Type	Required	Description
id	string	Required	Unique identifier for the chat completion. Chunks from the same streaming response share the same ID.
object	string	Required	Object type. Always chat.completion.chunk.
created	integer	Required	Unix timestamp, in seconds, of when the chat completion was created.
model	string	Required	The model used to generate the completion.
system_fingerprint	string	Optional	Fingerprint of the backend configuration that processed the request.
choices	array[object]	Required	A list of chat completion choices.
└ index	integer	Optional	The index of the generated choice.
└ delta	object	Optional	The incremental message content returned in the current chunk.
└ finish_reason	string or null	Optional	The reason generation stopped. Usually null for intermediate chunks and stop in the final chunk.

Response Example

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

...

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"content":" today"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"content":"?"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"claude-sonnet-4-20250514","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}