Chat Completion

Chat Completions

Endpoint: /api/chat/completions

Description: Generates a chat completion response using the specified model. Requires sufficient user credits and valid model access permissions.

Authentication: Required (JWT token or Api Key)

HTTP Method: POST

Request Format:

{
	"model": "llama3.3:70b-instruct-q8_0",
	"messages": [
		{
			"role": "user",
			"content": "Hello, can you help me with a coding problem?"
		}
	],
	"temperature": 0.7,
	"max_tokens": 500,
	"stream": true
}

Key Request Parameters:

Parameter	Type	Required	Description
model	string	Yes	ID of the model to use
messages	array	Yes	Array of message objects with role and content
temperature	number	No	Sampling temperature (0-2.0)
max_tokens	integer	No	Maximum tokens to generate
stream	boolean	No	Whether to stream the response

Response Format:

{
	"id": "chat-12345abcde",
	"object": "chat.completion",
	"created": 1707841963,
	"model": "llama3.3:70b-instruct-q8_0",
	"choices": [
		{
			"index": 0,
			"message": {
				"role": "assistant",
				"content": "I'd be happy to help with your coding problem. Could you please describe the issue you're facing in more detail? What programming language are you working with, and what specific problem are you trying to solve?"
			},
			"finish_reason": "stop"
		}
	],
	"usage": {
		"prompt_tokens": 24,
		"completion_tokens": 42,
		"total_tokens": 66
	}
}

Response Codes:

• 200: Successfully generated completion

• 402: Insufficient credits

• 403: Model access forbidden

• 404: Model not found