Data platform
BigQuery ML
Model prices vs the direct API
cloud.google.comChecked Sep 23, 2026
- Fee on tokens
- Not published
- BigQuery bytes processed (on-demand or editions) plus the underlying Vertex AI model charges billed directly by that service; no separate BigQuery per-token rate for LLM calls
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
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
Claude Sonnet 5n/avs $400.00 direct
GPT-6 Soln/avs $400.00 direct
Gemini 3.8 Flashn/avs $150.00 direct
DeepSeek V4.1 Flashn/avs $27.00 direct
100M input and 20M output tokens a month, paying with gateway credits.
The terms, in their words
BigQuery ML remote models that call Vertex AI (Gemini Enterprise Agent Platform) models such as Gemini and Claude from SQL via ML.GENERATE_TEXT.
- Markup
- BigQuery bytes processed (on-demand or editions) plus the underlying Vertex AI model charges billed directly by that service; no separate BigQuery per-token rate for LLM calls
- Providers
- Google models on Agent Platform, Anthropic Claude models enabled on Agent Platform, and open models deployed to Agent Platform
- The bytes processed by BigQuery are billed according to standard pricing such as on-demand or editions pricing.
- For remote endpoint model pricing, you are billed directly by the above services.
- Google models hosted on Gemini Enterprise Agent Platform ML.GENERATE_TEXT ML.GENERATE_EMBEDDING Generative AI on Gemini Enterprise Agent Platform batch pricing
BigQuery ML vs
Databricks Mosaic AI
Snowflake Cortex AI
Helicone
Kong AI Gateway
LiteLLM
Vercel AI GatewayBigQuery, the Gemini Enterprise Agent Platform (formerly Vertex AI), the Gemini API, Looker, AlloyDB and Spanner.
Pricing 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.