dbrx-instruct

This documentation is valid for the following list of our models:

• databricks/dbrx-instruct

Model Overview

A powerful, open-source large language model (LLM) developed by Databricks. It utilizes a fine-grained mixture-of-experts (MoE) architecture with 132 billion total parameters, of which 36 billion are active for any given input.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

Submit a request

API Schema

Generate a conversational response using a language model.

Creates a chat completion using a language model, allowing interactive conversation by predicting the next response based on the given chat history. This is useful for AI-driven dialogue systems and virtual assistants.

post

/v1/chat/completions

Authorizations

Body

max_tokensnumber · min: 1 · default: 512

streamboolean · default: false

ninteger · min: 1

seedinteger · min: 1

top_pnumber · min: 0.01 · max: 1

top_knumber

temperaturenumber

repetition_penaltynumber | nullable

logprobsboolean | nullable

echoboolean

min_pnumber · max: 1

presence_penaltynumber | nullable

frequency_penaltynumber | nullable

modelundefined · enumrequired

Options: databricks/dbrx-instruct

logit_biasobject | nullable

stream_optionsobject

stopany of

toolsobject[]

tool_choiceany of

response_formatone of

messagesone of[]required

Responses

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "max_tokens": 512,
    "stream": false,
    "n": 1,
    "seed": 1,
    "top_p": 1,
    "top_k": 1,
    "temperature": 1,
    "repetition_penalty": 1,
    "logprobs": true,
    "echo": true,
    "min_p": 1,
    "presence_penalty": 1,
    "frequency_penalty": 1,
    "model": "databricks/dbrx-instruct",
    "logit_bias": {
      "ANY_ADDITIONAL_PROPERTY": 1
    },
    "stream_options": {
      "include_usage": true
    },
    "stop": "text",
    "tools": [
      {
        "type": "function",
        "function": {
          "description": "text",
          "name": "text",
          "parameters": null
        }
      }
    ],
    "tool_choice": "none",
    "response_format": {
      "type": "text"
    },
    "messages": [
      {
        "name": "text",
        "role": "system",
        "content": "text"
      }
    ]
  }'

201

201

No body