Skip to main content
POST
https://vibetool.ai
/
v1
/
chat
/
completions
curl -X POST [https://vibetool.ai/v1/chat/completions](https://vibetool.ai/v1/chat/completions) \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

{
    "id": "chat_202512301050_99caf047",
    "object": "chat.completion",
    "model": "gpt-5.2",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! How can I help you?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 7,
        "completion_tokens": 15,
        "total_tokens": 22
    }
}

​
Authorization

​
Authorization
string
required
Bearer Token authentication. Format: Bearer YOUR_API_KEY

​
Body

​
model
enum<string>
default:"gpt-5.2"
required
Model name for chat completion.Available options: gpt-5.2Example: "gpt-5.2"
​
messages
object[]
required
List of messages for the conversation.Minimum array length: 1
​
stream
boolean
default:"false"
Whether to stream the response.
  • true: Stream response chunk by chunk in real-time
  • false: Wait for complete response and return all at once
Example: false
​
temperature
number
default:"1.0"
Sampling temperature, controls randomness of output.Notes:
  • Lower values (e.g. 0.2): more deterministic and focused output
  • Higher values (e.g. 1.5): more random and creative output
  • Required range: 0 <= x <= 2
Example: 0.7
​
top_p
number
default:"1.0"
Nucleus sampling parameter.Notes:
  • Controls sampling from tokens with cumulative probability
  • For example, 0.9 means sampling from tokens with top 90% cumulative probability
  • Recommendation: Do not adjust both temperature and top_p simultaneously
  • Required range: 0 <= x <= 1
Example: 0.9
​
top_k
integer
Top-K sampling parameter.Notes:
  • For example, 10 means only considering the top 10 most probable tokens during each sampling step
  • Smaller values make output more focused
  • Default: unlimited
  • Required range: x >= 1
Example: 40

​
Response Schema

Chat completion successful. Returns a chat completion object.
​
id
string
required
Unique identifier for the chat completion.
​
model
string
required
The model used for completion.
​
object
enum<string>
required
Response type.Available options: chat.completion
​
created
integer
Unix timestamp when the completion was created.
​
choices
object[]
required
List of completion choices.
​
usage
object
Token usage statistics.
curl -X POST [https://vibetool.ai/v1/chat/completions](https://vibetool.ai/v1/chat/completions) \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

{
    "id": "chat_202512301050_99caf047",
    "object": "chat.completion",
    "model": "gpt-5.2",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! How can I help you?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 7,
        "completion_tokens": 15,
        "total_tokens": 22
    }
}