Databricks Mosaic via VerticalAPI

Updated May 04, 2026·By VerticalAPI Team

Databricks Mosaic AI inference (DBRX, Llama 3.3, Mixtral) via VerticalAPI's OpenAI-compatible endpoint. BYOK with your Databricks PAT, zero markup, your data stays in your workspace.

Start free with your Databricks Mosaic key → Read the docs

Endpoint: https://api.verticalapi.com/v1/chat/completions · BYOK header: X-Provider-Key: dapi... + x-databricks-host header

Supported models

Databricks Mosaic models routed by VerticalAPI

Pass the model ID below as model in any OpenAI-compatible request. New Databricks Mosaic models are typically supported within 24h of release.

Model ID	Name	Context	Pricing (provider)
`databricks-dbrx-instruct`	DBRX Instruct	32K	Databricks DBU pricing
`databricks-meta-llama-3-3-70b-instruct`	Llama 3.3 70B (Databricks)	128K	Databricks DBU pricing
`databricks-mixtral-8x7b-instruct`	Mixtral 8x7B (Databricks)	32K	Databricks DBU pricing

Pricing reflects Databricks Mosaic's rates — you pay Databricks Mosaic directly. VerticalAPI adds zero markup on tokens.

Quickstart

5-line Databricks Mosaic call via VerticalAPI

Drop-in replacement for the OpenAI SDK. Works with the OpenAI Python client, Node, Go, curl — anything that speaks HTTP.

                databricks-mosaic_quickstart.py
                Python
            
from openai import OpenAI

client = OpenAI(
    base_url="https://api.verticalapi.com/v1",
    api_key="vapi_...",
    default_headers={"X-Provider-Key": "dapi..."}
)

response = client.chat.completions.create(
    model="databricks-meta-llama-3-3-70b-instruct",  # Databricks Mosaic
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Why use Databricks Mosaic via VerticalAPI

Four reasons developers route Databricks Mosaic through us

Zero token markup

You pay Databricks Mosaic directly with your own key. VerticalAPI's revenue is the gateway subscription, not a tax on your tokens.

One key, every provider

Databricks Mosaic alongside OpenAI, Anthropic, Gemini and 12 more — same OpenAI-compatible endpoint, same SDK, switchable per-request.

Latency & cost monitoring

Per-request token counts, p50/p95 latency and cost dashboards out of the box. Compare Databricks Mosaic to other providers on identical prompts.

Observability built in

Every Databricks Mosaic call gets a trace ID, replayable payload and audit log entry. Wire to Datadog or Sentry via OpenTelemetry.

Best for

Where Databricks Mosaic shines

data-residency in Databricks workspace Unity Catalog governance fine-tuned models on customer data lakehouse-integrated agents

FAQ

Common questions about Databricks Mosaic on VerticalAPI

How does data residency work?

Inference happens entirely within your Databricks workspace — VerticalAPI signs requests with your PAT and forwards them to your workspace URL. No prompts or completions leave your tenant.

What's special about DBRX?

DBRX is a 132B MoE model open-released by Databricks (2024) — strong for code and reasoning, available natively in any Databricks workspace via Mosaic AI Model Serving.

Switch providers

All supported LLM providers

Same endpoint, same SDK — just change the model and the BYOK header.

Ship on Databricks Mosaic in 60 seconds

Free tier — bring your own Databricks Mosaic key, zero markup, OpenAI-compatible endpoint.

Get your VerticalAPI key →