Databricks Mosaic AI
Model prices vs the direct API
- Fee on tokens
- List price
- DBUs per 1M tokens (Standard pay per token; Priority and Batch tiers separate)
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Dollar figures assume $0.07 per DBU, from the Azure Retail Prices API meter 'Premium Serverless Realtime Inferencing DBU' (Azure Databricks, East US 2); the Databricks pages render $ per DBU client side. Cross-check: Claude Sonnet 4.6 at 42.857 DBU x $0.07 = $3.00, equal to Anthropic list
Models on Databricks Mosaic AI
8 model routes. 5 of 6 at the lab's own list price; the rest shown as a premium or discount.
Claude Opus 5.5default region · direct $4 / $20$4 / $20same as direct$4 / $20None
Gemini 3.5 Flashdefault region · direct $1.5 / $9$1.88 / $11.3+25% vs direct$1.5 / $9+25%
GPT-5default region · direct $1.25 / $10$1.25 / $10same as direct$1.25 / $10None
Llama 3.3 70B Instructdefault region$0.5 / $1.5n/an/a
Premium: blended price (3 input to 1 output) on this platform against the lab's own API. Regions are separate routes.
Features
- Fallbacks
- Load balancing
- Caching
- Guardrails
- Observability
- Rate limits
- Budgets
- Prompts
- OpenAI-compatible
- Bring your own key
- Data residency
- Private networking
What it costs on real workloads
DeepSeek V4.1 Flash$27.00vs $27.00 direct
100M input and 20M output tokens a month, paying with gateway credits.
The terms, in their words
Databricks' pay-per-token Foundation Model APIs (open and proprietary models) with AI Gateway governance on the Databricks platform.
- Markup
- DBUs per 1M tokens (Standard pay per token; Priority and Batch tiers separate)
- Free tier
- 14-day free trial
- Providers
- Open models (Llama, gpt-oss, Qwen, Gemma, DeepSeek, GLM, Kimi) plus proprietary Anthropic Claude, OpenAI GPT, Google Gemini and xAI Grok
- ⌖ When regional processing (data residency) is enabled, models with the ⌖ label will have a 10% uplift applied (will be charged DBU rates 10% greater than those shown in the table above).
- Claude Sonnet 4.5, 4.6 ⌖ 42.857 214.286 (Standard Pay Per Token, DBU Per 1M Tokens, input / output)
- * The DBU rates for these Gemini models do not include a promotional discount of 20% (promotional pricing is 20% lower than shown).
Source: www.databricks.com/product/pricing/proprietary-foundation-model-serving
Databricks Mosaic AI vs
Snowflake Cortex AI
BigQuery ML
Helicone
Kong AI Gateway
LiteLLM
Vercel AI GatewayPricing as read from the gateway's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.