Google Vertex AI (Gemini Enterprise Agent Platform)
- Categories
- Hyperscaler AI platforms
- Owned by
- Alphabet Inc. (NASDAQ: GOOGL) · also owns Google Gemini API (AI Studio)
- HQ
- US
- Website
- https://cloud.google.com/vertex-ai
- Pricing page
- https://cloud.google.com/vertex-ai/generative-ai/pricing
- Fee model
- per_token
- Fees
- Per-token on-demand (Standard) pricing; Priority tier at a premium and Flex/Batch tier at ~50% of Standard for Gemini; partner MaaS models (Claude, Grok, DeepSeek, Qwen, GLM, Llama, gpt-oss, Mistral, MiniMax, Kimi) billed per token; Flexible Savings Plans (spend-based CUDs) available
- Free tier
- no (Google Cloud new-customer credits apply; Gemini grounding includes free query quotas)
- OpenAI-compatible API
- partial
- Bring your own key
- no
- Notes
- Page is now titled 'Agent Platform Pricing'. Gemini 3.x GA models: Global endpoint vs Non-global (regional) endpoints priced ~10% higher since 2026-07-01. Claude has regional price tabs (Global, US, EU, us-east5, ...) — regional ~10% above Global. Only 200-status requests billed. OpenAI-compatible Chat Completions endpoint exists for Gemini and some MaaS models (partial).
- Sources
- https://cloud.google.com/vertex-ai/generative-ai/pricing collected 2026-09-18
LLM prices (49 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Claude Fable 5 | $10 | $50 | $1 | — | ✓ src |
| Claude Fable 5.1 | $10 | $50 | $0.25 | — | ✓ src |
| Claude Haiku 4.5 | $1 | $5 | $0.10 | — | ✓ src |
| Claude Opus 4.1 | $15 | $75 | $1.50 | — | ✓ src |
| Claude Opus 4.5 | $5 | $25 | $0.50 | — | ✓ src |
| Claude Opus 4.6 | $5 | $25 | $0.50 | — | ✓ src |
| Claude Opus 4.7 | $5 | $25 | $0.50 | — | ✓ src |
| Claude Opus 4.8 | $5 | $25 | $0.50 | — | ✓ src |
| Claude Opus 5 | $5 | $25 | $0.50 | — | ✓ src |
| Claude Sonnet 4.5 | $3 | $15 | $0.30 | — | ✓ src |
| Claude Sonnet 4.6 | $3 | $15 | $0.30 | — | ✓ src |
| Claude Sonnet 5 | $2 | $10 | $0.20 | — | ✓ src |
| Codestral 2 | $0.30 | $0.90 | — | — | ✓ src |
| DeepSeek V3.1 | $0.60 | $1.70 | $0.06 | — | ✓ src |
| DeepSeek V3.2 | $0.56 | $1.68 | $0.056 | — | ✓ src |
| DeepSeek-OCR | $0.30 | $1.20 | — | — | ✓ src |
| Gemini 2.5 Flash gemini-2.5-flash |
$0.30 | $2.50 | $0.03 | — | ✓ src |
| Gemini 2.5 Flash-Lite gemini-2.5-flash-lite |
$0.10 | $0.40 | $0.01 | — | ✓ src |
| Gemini 2.5 Pro gemini-2.5-pro |
$1.25 | $10 | $0.125 | — | ✓ src |
| Gemini 3 Flash Preview gemini-3-flash-preview |
$0.50 | — | $0.05 | — | ◐ src |
| Gemini 3.1 Flash-Lite gemini-3.1-flash-lite |
$0.25 | $1.50 | $0.025 | — | ✓ src |
| Gemini 3.1 Pro Preview gemini-3.1-pro-preview |
$2 | $12 | $0.20 | — | ✓ src |
| Gemini 3.5 Flash gemini-3.5-flash |
$1.50 | $9 | $0.15 | — | ✓ src |
| Gemini 3.5 Flash-Lite gemini-3.5-flash-lite |
$0.30 | $2.50 | $0.03 | — | ✓ src |
| Gemini 3.6 Flash gemini-3.6-flash |
$0.75 | $3.75 | $0.075 | — | ✓ src |
| Gemini 3.7 Flash gemini-3.7-flash |
$0.75 | $3.75 | $0.075 | — | ✓ src |
| Gemini 3.8 Flash gemini-3.8-flash |
$0.75 | $3.75 | $0.075 | — | ✓ src |
| Gemini 3.8 Flash Cyber | $1.50 | $7.50 | $0.15 | — | ✓ src |
| GLM 4.7 | $0.60 | $2.20 | $0.06 | — | ✓ src |
| GLM 5 | $1 | $3.20 | $0.10 | — | ✓ src |
| GLM-5.2 | $1.40 | $4.40 | $0.14 | — | ✓ src |
| gpt-oss-120b | $0.09 | $0.36 | — | — | ✓ src |
| gpt-oss-20b | $0.07 | $0.25 | $0.007 | — | ✓ src |
| Grok 4.1 Fast (Reasoning / Non-Reasoning) | $0.20 | $0.50 | $0.05 | — | ✓ src |
| Grok 4.20 (Reasoning / Non-Reasoning) | $1.25 | $2.50 | $0.20 | — | ✓ src |
| Grok 4.3 | $1.25 | $2.50 | $0.20 | — | ✓ src |
| Grok 4.6 | $2 | $6 | $0.50 | — | ✓ src |
| Kimi K2 Thinking | $0.60 | $2.50 | $0.06 | — | ✓ src |
| Llama 3.3 70B Instruct | $0.72 | $0.72 | — | — | ✓ src |
| Llama 4 Maverick 17B Instruct | $0.35 | $1.15 | — | — | ✓ src |
| Llama 4 Scout 17B Instruct | $0.25 | $0.70 | — | — | ✓ src |
| MiniMax M2 | $0.30 | $1.20 | $0.03 | — | ✓ src |
| Mistral Medium 3 | $0.40 | $2 | — | — | ✓ src |
| mistral-small-3.1-24b-instruct | $0.10 | $0.30 | — | — | ✓ src |
| Qwen3 235B A22B 2507 | $0.22 | $0.88 | — | — | ✓ src |
| Qwen3 Coder 480B A35B | $0.22 | $1.80 | $0.022 | — | ✓ src |
| Qwen3 Next 80B A3B | $0.15 | $1.20 | — | — | ✓ src |
| Qwen3-Next-80B-Thinking | $0.15 | $1.20 | — | — | ✓ src |
| R1 0528 | $1.35 | $5.40 | — | — | ✓ src |