AIGROW vs Google Vertex AI

Google Cloud sells Gemini, Claude and Grok on the platform it long called Vertex AI and now calls Gemini Enterprise Agent Platform, at list price on the global endpoint and 10% more on regional ones, billed monthly to a Cloud account. AIGROW sells discounted prepaid credit for the same models through an OpenAI-compatible endpoint, with no Google Cloud project. The table compares the models both sell, price by price.

See the table

Every model both sell costs less per token through AIGROW credit than at Google Vertex AI, on input and on output.

9AIGROW vs Google Vertex AImodels both sell, priced side by side
Less through AIGROW credit
9 of 9
Google Vertex AI prices read
18 November 2026
Model check
11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
Sponsored placement
none
Nothing on this page is paid for by anyone.

Price per model: Google Vertex AI and AIGROW credit

USD per million tokens, input on the first line and output on the second. The difference is rounded so it never overstates a saving.

Prices per million tokens at Google Vertex AI and through AIGROW credit
ModelGoogle Vertex AIAIGROW creditDifference
Claude Opus 5.5$4.00$20.00$1.60$8.0060% less60% less
Claude Fable 5.2$8.00$40.00$3.20$16.0060% less60% less
Claude Sonnet 5.5$2.00$10.00$0.80$4.0060% less60% less
Claude Haiku 5.5$0.10$0.50$0.04$0.2060% less60% less
Grok 4.7$2.00$6.00$0.50$1.5075% less75% less
Gemini 4 Argon$2.00$10.00$1.00$5.0050% less50% less
Gemini 4 Hydrogen$1.50$7.50$0.75$3.7550% less50% less
Gemini 3.8 Flash$0.75$3.75$0.375$1.87550% less50% less
Claude Fable 5.1Previous version, replaced by Claude Fable 5.2$10.00$50.00$4.00$20.0060% less60% less

Google Vertex AI’s prices as published on 18 November 2026, each linked from its row. AIGROW’s are the rates the endpoint bills with, at the price credit sells for. Prices change, so check theirs before you decide.

Google’s prices here are its global endpoint at the standard rate on 18 November 2026. Regional endpoints cost 10% more. Google lists Gemini 4 Argon at $4 and $20 from 1 December 2026, and Gemini 3.8 Flash at $1.50 and $7.50 from 1 January 2027. Grok prompts of 200,000 tokens or more and Claude Haiku prompts of 100,000 or more are billed at higher long-context rates. Google also prints batch rates, which AIGROW does not have.

Fees and terms

What each one charges beyond the tokens, and what happens to credit you have not spent.

TermsAIGROWGoogle Vertex AI
Fee when you buy creditNone: $10 buys $40 of creditNone on the global endpoint; regional endpoints cost 10% more
Smallest purchase$10None: pay-as-you-go usage has no fixed term
Credit expiryNo expiry date in our TermsNo prepaid credit to expire: usage is billed monthly in arrears
RefundsSpent credit: never. Unspent credit: within 14 days of buying it, for consumers in the EU, EEA, UK and Switzerland.A billing error Google accepts comes back as a credit memo
PaymentCard, Apple Pay, Google Pay or Amazon Pay at the Stripe checkout; WeChat Pay, Pix, UPI or crypto for a one-off packThe payment method on the Google Cloud billing account, billed monthly
Models17 models from Anthropic, OpenAI, Google and xAIGoogle’s models and partner models from Anthropic, xAI and others

Google Vertex AI’s terms as published on the pages below, read on 18 November 2026. AIGROW’s are from our Terms of Service.

Google’s model pricing · Google’s partner model pricing · Google on OpenAI compatibility · Google Cloud Terms of Service

Is the model the one you paid for?

How each side shows that the model answering is the one it sells.

Google Vertex AI
Google makes Gemini and serves it itself, and its pricing page says partner models such as Claude and Grok are offered as managed APIs. As of 18 November 2026 we have not run our check on Google’s platform. The script below can produce a result for either side.
Certified genuine by AIGROW
On 11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026 we sent each model we sell the same prompts as the same model at its maker or through OpenRouter, and compared the answers, the prompt tokens and the tool calls. 9 of the 9 models on this page met our rule. This is AIGROW’s own check: no model maker reviewed or endorsed it. See every result and the method
Results of the model check of 11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
ModelHereAt the maker
Compared with Anthropic’s API
Claude Opus 5.512 of 1212 of 12
Claude Fable 5.212 of 1212 of 12
Claude Sonnet 5.512 of 1212 of 12
Claude Haiku 5.512 of 1212 of 12
Claude Fable 5.112 of 1212 of 12
Compared with the same model through OpenRouter
Grok 4.75 of 55 of 5
Gemini 4 Argon7 of 1212 of 12 with effort set to low11 of 126 of 12 with effort set to low
Gemini 4 Hydrogen0 of 1211 of 12 with effort set to medium12 of 1211 of 12 with effort set to medium
Gemini 3.8 Flash10 of 1211 of 12

A 2026 study by the CISPA Helmholtz Center for Information Security tested 17 unofficial APIs that claim to give access to the makers’ models, and found identity verification failures in 45.83% of its fingerprint tests. It left out routing platforms that disclose where they send requests, such as OpenRouter. Any seller below list price can be checked with the script below, AIGROW included. Read the study.

Run the check yourself

Tests Google’s Gemini 4 Hydrogen beside the same model through OpenRouter, with a Google Cloud access token and an OpenRouter key as the reference. To test AIGROW the same way, leave out --base and MAKER_MODEL, use an AIGROW key and name the model gemini-4-hydrogen.

MODEL_CHECK_KEY=$(gcloud auth print-access-token) MAKER_KEY=sk-or-your_key MAKER_MODEL=google/gemini-4-hydrogen node model-check.mjs --base https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi google/gemini-4-hydrogen

Download model-check.mjs

Every request is billed as usual. The battery is the costly one: a few cents of credit on most models, more when a model thinks for long. To test another seller’s API, pass its address with --base.

When Google Vertex AI is the better choice

Inside your Google Cloud project
Usage is billed monthly to a Cloud billing account and requests are signed with Google Cloud credentials. AIGROW is a separate prepaid account with its own keys.
Regional endpoints, batch and priority rates
Google prints regional and multi-region prices at 10% above global, batch rates for Claude and Gemini, and a priority rate for Gemini. AIGROW has one rate per model and no regional endpoint.
Gemini from its maker, on its native API
Google serves Gemini on its own generateContent API as well as an OpenAI-compatible one, and prices image generation and model tuning on the same page. AIGROW takes chat requests in the OpenAI and Anthropic formats.

Switching from Google Vertex AI

A base URL and a key that starts with ag_, created in API access on the dashboard.

  • At Google Vertex AI today: base URL https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi
  • Anthropic SDK and Claude Code: base URL https://aigrow.gg
  • OpenAI SDK, Cline, Aider, OpenCode: base URL https://aigrow.gg/v1
  • Model ids: ours, such as gemini-4-hydrogen, and Google Vertex AI’s spelling, such as google/gemini-4-hydrogen, both work.

Some lines behave differently from the maker’s endpoint, for example on max_tokens and on the starting reasoning effort: the model check lists each difference with its numbers. Codex sends Responses API requests, which this endpoint does not take.

The setup guide covers every other tool, and the Claude Code page walks through its settings one by one.

For the models in the table, Google’s global endpoint bills list price and its regional endpoints 10% more. The table sets each model’s price through AIGROW credit beside it, with the difference worked out from the rates our endpoint bills with. Google also prints batch rates below its standard ones, which AIGROW does not offer.

Yes. Google’s Vertex AI addresses now redirect to Gemini Enterprise Agent Platform, and its pricing page is titled Agent Platform Pricing. This page keeps the Vertex AI name because many people still search for it.

Google serves Gemini itself and says partner models are offered as managed APIs. Run the same test on both. Our public script sends any endpoint twelve questions with one right answer, a two-word prompt, four short questions and a tool call, and prints the score and the prompt tokens beside the same model at its maker or through OpenRouter. We have not run it on Google’s platform.

Those that send OpenAI Chat Completions or Anthropic Messages requests do: set the base URL https://aigrow.gg/v1, use an AIGROW key in place of the Google access token, and keep the model id, with or without the google/ prefix, such as gemini-4-hydrogen. Code written for the native generateContent API does not.

No. Google’s terms say pay-as-you-go usage is billed monthly in arrears, so there is no balance to top up or to expire. AIGROW is prepaid: you buy credit and requests draw on it. AIGROW’s Terms set no expiry date for credit. Spent credit is not refunded, and consumers in the EU, EEA, UK and Switzerland can have unspent credit refunded within 14 days of buying it.

No. AIGROW is independent and is not affiliated with, endorsed by or sponsored by Google. The Vertex AI and Gemini names identify Google’s products only.

Run your own workload on both, then compare the bills.

Start with the $10 pack, run your real workload against it, and check the dashboard before buying more.

Monthly plans or one-off packs · redemption code delivered at once · usage dashboard included