Best LLM Inference Providers

Vendor profileChecked Nov 8, 2026

Google Cloud Vertex AI (Gemini Enterprise Agent Platform)

Google Cloud; Google's documentation now names Vertex AI Platform "Gemini Enterprise Agent Platform" · cloud.google.com · Last checked:

  • Cloud provider platform
  • Serverless per-token API
  • Provisioned throughput
  • Bring-your-own-model (Model Garden self-deploy)

Company status

Active. A Google Cloud service and business line of Google (Alphabet Inc.). Google renamed several Vertex AI products under Gemini Enterprise Agent Platform.

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Capabilities

  • Gemini and other proprietary and open-weight models billed per token
  • OpenAI-compatible Chat Completions endpoint for Gemini models and select self-deployed Model Garden models
  • Self-deploy open models (for example via vLLM or HF TGI containers) from Model Garden
  • Google states it won't train on customer data without permission; Gemini models cache data by default for up to 24 hours, with documented steps toward zero data retention
  • Security controls for generative AI including data residency at rest, CMEK, and VPC Service Controls

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Who it tends to fit

  • Teams on Google Cloud that want Gemini plus open models under one project and IAM
  • Buyers who need documented data residency and VPC Service Controls

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Pricing

Published per-token pricing on https://cloud.google.com/vertex-ai/generative-ai/pricing (for example, introductory pricing of $0.75 / $3.75 per 1M input / output tokens for Gemini 3.8 Flash through December 31, 2026).

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Published certifications

  • SOC 2 (Generative AI on Gemini Enterprise Agent Platform in scope)
  • ISO 27001 (Generative AI on Gemini Enterprise Agent Platform in scope)
  • HIPAA (Generative AI on Agent Platform listed as a covered product)

Listed as stated by the vendor. Scope can differ by product or subsidiary; request current reports.

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Limitations to check

  • Zero data retention needs configuration: caching is on by default, some grounding features store data and cannot be disabled, and ZDR for some partner models requires approval
  • Google may log prompts for abuse detection under its terms
  • Product names changed from Vertex AI; check current names in contracts and docs

Sources 1, 2, 3, 4, 5, 6, 7 · checked 2026-11-08

Sources

  1. Pricing page lists per-1M-token prices, including introductory Gemini 3.8 Flash pricing through December 31, 2026cloud.google.com/vertex-ai/generative-ai/pricingChecked 2026-11-08
  2. No training on customer data without permission; default caching deleted within 24 hours; abuse-monitoring logging; feature-by-feature zero data retention stepsdocs.cloud.google.com/vertex-ai/generative-ai/docs/data-governanceChecked 2026-11-08
  3. Chat Completions API works as an OpenAI-compatible endpoint for Gemini and select self-deployed Model Garden modelsdocs.cloud.google.com/vertex-ai/generative-ai/docs/migrate/openai/overviewChecked 2026-11-08
  4. ISO 27001 page lists Generative AI on Gemini Enterprise Agent Platform (formerly Generative AI on Vertex AI)cloud.google.com/security/compliance/iso-27001Checked 2026-11-08
  5. SOC 2 page lists Generative AI on Gemini Enterprise Agent Platform (formerly Generative AI on Vertex AI)cloud.google.com/security/compliance/soc-2Checked 2026-11-08
  6. HIPAA page lists Generative AI on Agent Platformdocs.cloud.google.com/docs/security/compliance/hipaaChecked 2026-11-08
  7. Name changes page: some Vertex AI products renamed with the introduction of Gemini Enterprise Agent Platformdocs.cloud.google.com/gemini-enterprise-agent-platform/vertex-ai-name-changesChecked 2026-11-08

Report a correction: [email protected]. Facts are re-checked at least every 90 days.