Databricks: DBRX 132B Instruct (nitro)

databricks/dbrx-instruct:nitro

Updated Apr 332,768 context
$0.9/M input tkns$0.9/M output tkns

DBRX is a new open source large language model developed by Databricks. At 132B, it outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7B on standard industry benchmarks for language understanding, programming, math, and logic.

It uses a fine-grained mixture-of-experts (MoE) architecture. 36B parameters are active on any input. It was pre-trained on 12T tokens of text and code data. Compared to other open MoE models like Mixtral-8x7B and Grok-1, DBRX is fine-grained, meaning it uses a larger number of smaller experts.

See the launch announcement and benchmark results here.

#moe

Note: this is a higher-throughput version of this model, and may have higher prices and slightly different outputs.

OpenRouter attempts providers in this order unless you set dynamic routing preferences. Prices displayed per million tokens.