Databricks Mosaic AI
Data platform · list price
Unverified
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
GPT-5.4default region · direct $2.5 / $15$2.5 / $15same as direct$2.5 / $15None
Gemini 3.5 Flashdefault region · direct $1.5 / $9$1.88 / $11.3+25% vs direct$1.5 / $9+25%
Claude Sonnet 4.6default region · direct $3 / $15$3 / $15same as direct$3 / $15None
Llama 3.3 70B Instructdefault region$0.5 / $1.5n/an/a
gpt-oss-120bdefault region$0.15 / $0.6n/an/a
GPT-5default region · direct $1.25 / $10$1.25 / $10same as direct$1.25 / $10None
Claude Haiku 4.5default region · direct $1 / $5$1 / $5same as direct$1 / $5None
Premium: blended price (3 input to 1 output) on this platform against the lab's own API. Regions are separate routes.
Carries 62 of the models tracked here, from its own model catalog, checked Nov 9, 2026.
About Databricks Mosaic AI
Databricks' pay-per-token Foundation Model APIs (open and proprietary models) with AI Gateway governance on the Databricks platform.
- Fee on tokens
- List price
- Pricing model
- DBUs per 1M tokens (Standard pay per token; Priority and Batch tiers separate)
- Bring your own key
- No
- 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
Features stated: none found. Not stated: Fallbacks, Load balancing, Caching, Guardrails, Observability, Rate limits, Budgets, Prompts, OpenAI-compatible, Bring your own key, Data residency, Private networking.
The terms, in their words
- 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 vsSnowflake Cortex AIBigQuery MLHeliconeKong AI GatewayLiteLLMNeon AI Gateway