DBRX Instruct on DeepInfra

DBRX · Databricks Mosaic

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

Why use DBRX Instruct on DeepInfra?

DeepInfra offers DBRX Instruct with pay-as-you-go pricing at $0.60/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.

Compare DBRX Instruct across 6 providers to find the best fit for your use case
Input / 1M
$0.60
Output / 1M
$1.20
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export DEEPINFRA_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
Model ID
dbrx-instruct

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="dbrx-instruct",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
  • The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.

Compare DBRX Instruct Across Providers

ProviderInput (per 1M)Output (per 1M)
Microsoft Foundry$2.70$2.70
Databricks Foundation Model Serving$0.75$2.25
Together AI$1.20$1.20
NVIDIA NIM——
DeepInfra$0.60$1.20
View all 6 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.60
Output tokens$1.20

Capabilities

Structured Outputs

About DBRX Instruct

DBRX Instruct, developed by Databricks, is a cutting-edge large language model designed for various natural language processing tasks. It excels in text summarization, question answering, information extraction, and code generation, utilizing a fine-grained mixture-of-experts architecture with 132 billion parameters. With advanced features like rotary position encodings, gated linear units, and grouped query attention, it performs exceptionally across multiple benchmarks, even outperforming some closed-source models. Trained on a vast 12 trillion token dataset, it supports contexts up to 32,000 tokens. Although primarily effective in English, its multilingual strength isn't fully explored.

Get Started