Text Generation API

Generate text using the chat completion endpoint. Supports GPT-4o, Claude, Gemini and more.

Endpoint

The chat completion endpoint:

http

POST https://api.tk-novalink.com/v1/chat/completions

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model name, e.g. gpt-4o
messages	array	Yes	Array of chat messages
temperature	number	No	Sampling temperature, 0-2
max_tokens	integer	No	Max tokens to generate
stream	boolean	No	Whether to stream the response

Request Example

bash

curl -X POST "https://api.tk-novalink.com/v1/chat/completions" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Streaming Response

Set stream=true to enable streaming responses:

bash

curl -X POST "https://api.tk-novalink.com/v1/chat/completions" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Supported Models

Commonly used text generation models:

Model	Description	Context Window
gpt-4o	OpenAI flagship model	128K
gpt-4o-mini	Lightweight model	128K
claude-sonnet-4	Anthropic coding workhorse	200K
gemini-2.5-pro	Google multimodal	1M
deepseek-v3	High cost-performance	64K

Embeddings API