Vertex AI pricing, checked at the source
Prices for Gemini, partner and open models on Google Cloud Vertex AI, read off Google Cloud's own pricing page with a link on every row. Estimate a monthly bill below.
Vertex AI prices per 1M tokens
Standard prices in USD. Each row links to Google Cloud's pricing page and shows the day we checked it.
| Model | Input | Cached input | Output | Batch (in / out) | Notes | Source |
|---|---|---|---|---|---|---|
| Gemini 4 ArgonGlobal endpoint | $2.00 | $0.10 | $10.00 | $1.00 / $5.00 | Promo price through November 30, 2026. From December 1, 2026: $4 in, $0.20 cached, $20 out. Batch promo: $1 in, $5 out. | Sourcechecked 2026-10-25 |
| Gemini 3.8 FlashGlobal endpoint | $0.75 | $0.075 | $3.75 | none listed | Intro price through December 31, 2026. From January 1, 2027: $1.50 in, $0.15 cached, $7.50 out. | Sourcechecked 2026-10-25 |
| Gemini 3.1 Pro Previewprompts up to 200K | $2.00 | $0.20 | $12.00 | $1.00 / $6.00 | Over 200K: $4 in, $0.40 cached, $18 out. Flex/Batch: $1 in, $6 out. | Sourcechecked 2026-10-25 |
| Gemini 3.5 FlashGlobal endpoint | $1.50 | $0.15 | $9.00 | $0.75 / $4.50 | Batch: $0.75 in, $4.50 out. | Sourcechecked 2026-10-25 |
| Gemini 3.5 Flash-LiteGlobal endpoint | $0.30 | $0.03 | $2.50 | none listed | Sourcechecked 2026-10-25 | |
| Claude Opus 5.5Global endpoint | $4.00 | $0.20 | $20.00 | none listed | 5m cache write $5. Page lists batch input $2.50 and batch output $12.50. | Sourcechecked 2026-10-25 |
| Claude Sonnet 5.5Global endpoint | $2.00 | $0.10 | $10.00 | $1.00 / $5.00 | Batch: $1 in, $5 out. | Sourcechecked 2026-10-25 |
| Claude Haiku 5.5prompts up to 200K | $0.10 | $0.01 | $0.50 | $0.05 / $0.25 | Over 200K: $0.50 in, $2.50 out. Batch: $0.05 in, $0.25 out. | Sourcechecked 2026-10-25 |
| DeepSeek-V3.2 | $0.56 | $0.056 | $1.68 | $0.28 / $0.84 | Batch: $0.28 in, $0.84 out. | Sourcechecked 2026-10-25 |
| Llama 4 Maverick | $0.35 | none listed | $1.15 | $0.175 / $0.575 | Batch: $0.175 in, $0.575 out. gpt-oss-120b is $0.09 in, $0.36 out on the same page. | Sourcechecked 2026-10-25 |
Terms on this page: Token · Prompt caching · Context window · Batch API
Estimate your Google Cloud bill
Enter your monthly tokens and how they split between new input, cached input and output. The result updates as you type.
Write 40k, 250M or 5B. Input, cached input and output tokens together.
100M tokens a month costs from $6.78 (Claude Haiku 5.5) to $259.60 (Claude Opus 5.5).
| Model | Per month | Per 1M tokens at this split |
|---|---|---|
| Claude Haiku 5.5prompts up to 200K | $6.78 | $0.0678 |
| Gemini 3.5 Flash-LiteGlobal endpoint | $25.34 | $0.2534 |
| DeepSeek-V3.2 | $32.37 | $0.32368 |
| Llama 4 Maverick | $39.00 | $0.39 |
| Gemini 3.8 FlashGlobal endpoint | $50.85 | $0.5085 |
| Gemini 3.5 FlashGlobal endpoint | $109.20 | $1.092 |
| Gemini 4 ArgonGlobal endpoint | $129.80 | $1.298 |
| Claude Sonnet 5.5Global endpoint | $129.80 | $1.298 |
| Gemini 3.1 Pro Previewprompts up to 200K | $145.60 | $1.456 |
| Claude Opus 5.5Global endpoint | $259.60 | $2.596 |
Standard prices in USD on 2026-10-25, before tax. Long-prompt tiers are left out; see the price table.
Google Cloud embeddings prices
Prices per 1M input tokens. Embedding models have no output price.
| Model | Price as listed | Per 1M tokens | Notes | Source |
|---|---|---|---|---|
| Gemini Embedding 2 (Unified Multimodal, Preview)online requests, text input | $0.20 per 1M tokens | $0.20 | Batch: $0.10. No charge for output tokens. | Sourcechecked 2026-10-25 |
Google Cloud image generation prices
Prices per image where the vendor lists one. Rows billed per megapixel or per token show how they bill instead.
| Model | Price as listed | Per image | Notes | Source |
|---|---|---|---|---|
| Imagen 4 Fastimage generation | $0.02 per image | $0.02 | Sourcechecked 2026-10-25 | |
| Imagen 4image generation | $0.04 per image | $0.04 | Sourcechecked 2026-10-25 | |
| Imagen 4 Ultraimage generation | $0.06 per image | $0.06 | Sourcechecked 2026-10-25 |
Write 500, 10k or 1M.
1k images a month costs from $20.00 (Imagen 4 Fast) to $60.00 (Imagen 4 Ultra).
| Model | Per month | Per image |
|---|---|---|
| Imagen 4 Fastimage generation | $20.00 | $0.02 |
| Imagen 4image generation | $40.00 | $0.04 |
| Imagen 4 Ultraimage generation | $60.00 | $0.06 |
List prices in USD on 2026-10-25, before tax, free tiers and add-ons. Rows billed another way are in the price table only.
How the bill is worked out
Only successful calls are billed
Global vs non-global
Long prompts
Batch and promos
Vertex AI pricing questions
How much does the Vertex AI cost?
Google Cloud bills its language models per million tokens, with separate prices for input, cached input and output. On 2026-10-25, standard prices ran from $0.10 (Claude Haiku 5.5) to $4.00 (Claude Opus 5.5) per 1M input tokens, and $0.50 (Claude Haiku 5.5) to $20.00 (Claude Opus 5.5) per 1M output tokens. Embeddings runs from $0.20 per 1M tokens. Image generation runs from $0.02 (Imagen 4 Fast) to $0.06 (Imagen 4 Ultra) per image.
Does Google Cloud offer a batch discount?
On some models. Batch prices are listed for Gemini 4 Argon, Gemini 3.1 Pro Preview, Gemini 3.5 Flash, Claude Sonnet 5.5, Claude Haiku 5.5, DeepSeek-V3.2, Llama 4 Maverick. The price table shows which rows have one.
Where do these prices come from?
From Google Cloud's own pricing page, https://cloud.google.com/vertex-ai/generative-ai/pricing, checked on 2026-10-25. Every row links to it. When a price cannot be confirmed, the row says to check the vendor's page instead of showing a number.
Does Vertex AI bill failed requests?
No. Google's page says you pay only for requests that return a 200 code; 4xx and 5xx errors are not charged.
Compare and plan
Building with the Vertex AI? OceanLab builds AI into business workflows, with people kept in charge. AI automation →
