How do I use Databricks models through the OpenRouter API?

OpenRouter serves 1 Databricks model behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as databricks/dbrx-instruct. The quickstart has request examples for every supported SDK.

Which Databricks model has the largest context window?

DBRX 132B Instruct has the largest context window of any Databricks model on OpenRouter, accepting up to 32,768 tokens per request.

What is the newest Databricks model on OpenRouter?

DBRX 132B Instruct is the most recently added Databricks model on OpenRouter, listed on March 29, 2024.

Databricks

Access 1 Databricks model through the OpenRouter unified API including DBRX 132B Instruct. Compare pricing, context windows, benchmarks, and capabilities between different Databricks models.

Databricks requests made on OpenRouter

Not enough data to display yet.

Databricks: DBRX 132B InstructDBRX 132B Instruct
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
by databricksMar 29, 202433K context

Databricks

Access 1 Databricks model through the OpenRouter unified API including DBRX 132B Instruct. Compare pricing, context windows, benchmarks, and capabilities between different Databricks models.

Databricks requests made on OpenRouter

Not enough data to display yet.

Databricks: DBRX 132B InstructDBRX 132B Instruct
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
by databricksMar 29, 202433K context

Databricks

Not enough data to display yet.

Frequently asked questions

Databricks

Not enough data to display yet.

Frequently asked questions