curl -X POST https://www.blackbox.ai/api/v1/chat \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "blackbox-chat",
  "messages": [
    {
      "role": "user",
      "content": "Write a short story about an astronaut."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 256,
  "stream": false
}'

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "blackbox-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The lone astronaut, Commander Eva, stared out at the swirling nebula..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 50,
    "total_tokens": 62
  }
}
This endpoint generates a response from the model based on a conversation history. 
curl -X POST https://www.blackbox.ai/api/v1/chat \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "blackbox-chat",
  "messages": [
    {
      "role": "user",
      "content": "Write a short story about an astronaut."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 256,
  "stream": false
}'

​
Request Body

​
model
string
required
The ID of the model to use. See the Models page for available options.
​
messages
array
required
An array of message objects representing the conversation history. Each object must have a role (user or assistant) and content (the message text).
​
stream
boolean
Defaults to false. If set to true, the response will be streamed back in chunks as it’s generated.
​
max_tokens
integer
The maximum number of tokens to generate in the completion. Defaults to 1024.
​
temperature
number
Controls randomness. A lower value (e.g., 0.2) makes the output more deterministic, while a higher value (e.g., 0.8) makes it more random. Defaults to 1.
​
top_p
number
An alternative to sampling with temperature, called nucleus sampling. Defaults to 1.
​
agent
string
An optional parameter to specify a specialized agent for the task.
​
response_format
object
An object specifying the format that the model must output. Setting { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "blackbox-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The lone astronaut, Commander Eva, stared out at the swirling nebula..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 50,
    "total_tokens": 62
  }
}