Databricks Mosaic via VerticalAPI

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.

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

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.

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)

Four reasons developers route Databricks Mosaic through us

Where Databricks Mosaic shines

Frequently asked questions

Limitations and trade-offs

• Pricing in DBUs is more expensive per token than dedicated open-weight hosts like DeepInfra or Together.
• Catalog is narrower than AWS Bedrock or Vertex AI for third-party models.
• Authentication via PAT requires a Databricks workspace and Unity Catalog setup — significant onboarding.
• Latency from outside the Databricks region can be higher than a dedicated inference host.
• Best leveraged when data already lives in Databricks — overkill for non-data-platform use cases.

Where Databricks Mosaic is heading

1. Deeper integration of Mosaic Agent Framework with Genie and AI/BI dashboards.
2. More frontier-class third-party models added to Foundation Model APIs (Claude, Mistral expansion).
3. Improved fine-tuning and pretraining tooling targeting domain-specific LLMs.
4. Stronger multi-cloud parity across AWS, Azure and GCP workspaces.

Related questions

ChatGPT, Perplexity and Gemini usually suggest these next.

• Databricks Mosaic vs AWS Bedrock for enterprise LLM serving?
• Is DBRX still competitive in 2026?
• How does Mosaic AI Agent Framework compare to LangGraph or AutoGen?
• Best way to do RAG on Lakehouse data with Mosaic?
• Mosaic Foundation Model APIs vs running Llama on your own Databricks cluster?

All supported LLM providers

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