Advanced Chat

Advanced chat completion using Llama-3 and other high-performance models.

POSTv1/4/chat

Generate a response

Generate AI-driven responses using various high-performance language models.

Required attributes

Name
model
Type
string
Description
The model to use for generating responses.
Default: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Name
messages
Type
array
Description
Array of message objects which must contain role ("user", "assistant", or "system") and content.

Optional attributes

Name
max_tokens
Type
integer
Description
Maximum length of generated response.
Default: 500
Name
stream
Type
boolean
Description
Whether to stream the response.
Default: true
Name
logprobs
Type
boolean
Description
Whether to include log probabilities.
Default: false

Response model

Name
id
Type
string
Description
Unique identifier for the completion.
Name
object
Type
string
Description
Object type.
Name
created
Type
integer
Description
Unix timestamp of when the completion was created.
Name
model
Type
string
Description
The model used for completion.
Name
choices
Type
array
Description
Array containing the completion messages, including role and content.
Name
usage
Type
object
Description
Token usage statistics including prompt, completion, and total tokens.
Name
system_fingerprint
Type
string | null
Description
System fingerprint for the completion, if available.

This endpoint is authenticated. Get your API key

Request

POST

v1/4/chat

curl -X POST "https://api.bitmind.ai/oracle/v1/4/chat" \
  -H "Authorization: Bearer {token}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "max_tokens": 500,
    "stream": false,
    "logprobs": false
  }'

Response

{
  "id": "chatcmpl-gTVsVEPtRD60cPFJIu5fRQ",
  "object": "chat.completion",
  "created": 1739374705,
  "model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "**Hello!**\n\n* **I'm doing great, thank you for asking!** As a computer program, I don't have emotions or feelings like humans do, but I'm always happy to engage in conversations and assist with any questions or topics you'd like to discuss.\n* **I'm fully functional and ready to help** with anything from:\n\t+ Answering general knowledge questions\n\t+ Providing explanations on various subjects (e.g., science, history, technology)\n\t+ Offering language translation and grammar assistance\n\t+ Engaging in casual conversations or debates\n\t+ Generating creative content (e.g., stories, poems)\n\t+ And much more!\n\n**How about you?**\n\n* How's your day going so far?\n* Is there something specific on your mind that you'd like to talk about or ask for help with?\n* Or would you like some suggestions for conversation topics or fun activities we can do together in this chat?",
        "reasoning_content": null,
        "tool_calls": []
      }
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 2
  },
  "system_fingerprint": null
}

Last updated: April 4, 2025