Google Vertex AI
Model prices vs the direct API
- Fee on tokens
- List price
- Per 1M tokens on your Google Cloud bill; partner models at the lab's list price on the Global endpoint, regional/multi-region endpoints about 10% more
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Models on Google Vertex AI
96 model routes. 39 of 84 at the lab's own list price; the rest shown as a premium or discount.
Claude Fable 5.1global · direct $10 / $50$10 / $50same as direct$10 / $50None
Gemini 3.8 Flashglobal-flex · direct $0.75 / $3.75$0.375 / $1.88-50% vs direct$0.75 / $3.75-50%
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
GPT-6 Sol$400.00vs $400.00 direct
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
Google Cloud's managed generative AI service serving Gemini plus partner (Anthropic Claude) and open models (Llama, Mistral, gpt-oss, others) per token.
- Markup
- Per 1M tokens on your Google Cloud bill; partner models at the lab's list price on the Global endpoint, regional/multi-region endpoints about 10% more
- Providers
- Gemini 2.5/3.x families, Anthropic Claude, Meta Llama, Mistral, OpenAI gpt-oss, GLM, and others listed on the pricing page
- You're charged only for requests that return a 200 response code.
- * For non-global endpoints, pricing will go into effect for the Generally available Gemini 3 and later families of all Google models starting on July 1, 2026. Before July 1, 2026, Global endpoint pricing applies to Non-global endpoints.
- Partner models are a curated list of generative AI models developed by Google partners. Partner models are offered as managed APIs.
Source: cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
Google Vertex AI vs
AWS Bedrock
Azure AI Foundry
IBM watsonx.ai
OCI Generative AI
Helicone
Kong 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.