DBRX Instruct on Together AI

DBRX · Databricks Mosaic

ServerlessOpen Weights

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

Why use DBRX Instruct on Together AI?

Together AI offers DBRX Instruct with pay-as-you-go pricing at $1.20/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

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

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="dbrx-instruct",
Model ID
dbrx-instruct

Request example

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="dbrx-instruct",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
  • The examples expect TOGETHER_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$1.20
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