Google Cloud

Google Vertex AI Pricing

Google Vertex AI resells 102 large language models from 6 vendors, billed per million tokens through Google Cloud. Mistral Nemo Latest (Mistral) is the cheapest at $0.150 per 1M output tokens. Anthropic Claude models on Vertex run $1.25–$25.00 per 1M output. Prices are USD, current as of July 20, 2026.

Vertex AI is Google Cloud's managed model platform. Alongside Google's own Gemini family it resells Anthropic Claude, Meta Llama, Mistral, DeepSeek and Qwen as managed endpoints — all billed per token on the same GCP invoice, with IAM, VPC Service Controls and committed-use discounts applying across the board.

Last updated · synced weekly from the upstream model catalog

Anthropic

$1.25/1M

from Claude 3 Haiku

Google

$0.250/1M

from GPT OSS 20B

Meta

$0.700/1M

from Meta Llama 4 Scout 17B 128e Instruct Maas

Mistral

$0.150/1M

from Mistral Nemo Latest

DeepSeek

$1.68/1M

from DeepSeek Ai DeepSeek V3.2 Maas

Qwen

$1.00/1M

from Qwen Qwen3 235B A22b Instruct 2507 Maas

Pricing by model

All prices in USD per 1 million tokens. Showing 80 of 102 priced models, cheapest first.

ModelVendorInput / 1MOutput / 1MContext
Mistral Nemo LatestMistral$0.150$0.150128K
GPT OSS 20B
ReasoningTools
Google$0.070$0.250131K
Gemini 2.0 Flash LiteGoogle$0.075$0.3001.0M
Gemini 2.0 Flash Lite 001Google$0.075$0.3001.0M
GPT OSS 120B
ReasoningTools
Google$0.090$0.360131K
Gemini 2.0 FlashGoogle$0.100$0.4001.0M
Gemini 2.5 Flash Lite Preview 06.17Google$0.100$0.4001.0M
Gemini 2.5 Flash Lite Preview 09 2025Google$0.100$0.4001.0M
Gemini 2.5 Flash-Lite
VisionReasoningToolsCache
Google$0.100$0.4001.0M
Xai Grok 4.1 Fast Non ReasoningGoogle$0.200$0.5002.0M
Xai Grok 4.1 Fast ReasoningGoogle$0.200$0.5002.0M
Codestral 2405Mistral$0.200$0.600128K
Codestral 2501Mistral$0.200$0.600128K
Codestral LatestMistral$0.200$0.600128K
Gemini 2.0 Flash 001Google$0.150$0.6001.0M
Meta Llama 4 Scout 17B 128e Instruct MaasMeta$0.250$0.70010.0M
Meta Llama 4 Scout 17B 16e Instruct MaasMeta$0.250$0.70010.0M
Llama 3.3 70B Instruct
Tools
Google$0.720$0.720128K
Qwen3 235B A22B Instruct
ReasoningTools
Google$0.220$0.880262K
Codestral 2Mistral$0.300$0.900128K
Codestral 2 001Mistral$0.300$0.900128K
Mistralai Codestral 2Mistral$0.300$0.900128K
Mistralai Codestral 2 001Mistral$0.300$0.900128K
Qwen Qwen3 235B A22b Instruct 2507 MaasQwen$0.250$1.00262K
Llama 4 Maverick 17B 128E Instruct
VisionTools
Google$0.350$1.15524K
Meta Llama 4 Maverick 17B 128e Instruct MaasMeta$0.350$1.151.0M
Meta Llama 4 Maverick 17B 16e Instruct MaasMeta$0.350$1.151.0M
Qwen Qwen3 Next 80B A3b Instruct MaasQwen$0.150$1.20262K
Qwen Qwen3 Next 80B A3b Thinking MaasQwen$0.150$1.20262K
Claude 3 HaikuAnthropic$0.250$1.25200K
Gemini 3.1 Flash Lite
VisionReasoningToolsCache
Google$0.250$1.501.0M
Gemini 3.1 Flash Lite Preview
VisionReasoningToolsCache
Google$0.250$1.501.0M
Gemini Flash-Lite Latest
VisionReasoningToolsCache
Google$0.250$1.501.0M
DeepSeek Ai DeepSeek V3.2 MaasDeepSeek$0.560$1.68164K
DeepSeek V3.2
ReasoningToolsCache
Google$0.560$1.68164K
DeepSeek V3.1
ReasoningTools
Google$0.600$1.70164K
Mistral Medium 3Mistral$0.400$2.00128K
Mistral Medium 3 001Mistral$0.400$2.00128K
Mistralai Mistral Medium 3Mistral$0.400$2.00128K
Mistralai Mistral Medium 3 001Mistral$0.400$2.00128K
GLM-4.7
ReasoningTools
Google$0.600$2.20200K
Gemini 2.5 Flash
VisionReasoningToolsCache
Google$0.300$2.501.0M
Gemini 2.5 Flash Preview 09 2025Google$0.300$2.501.0M
Gemini Robotics Er 1.5 PreviewGoogle$0.300$2.501.0M
Kimi K2 Thinking
ReasoningTools
Google$0.600$2.50262K
Gemini 3 Flash Preview
VisionReasoningToolsCache
Google$0.500$3.001.0M
Mistral Nemo 2407Mistral$3.00$3.00128K
Mistral Small 2503Mistral$1.00$3.00128K
Mistral Small 2503 001Mistral$1.00$3.0032K
GLM-5
ReasoningToolsCache
Google$1.00$3.20203K
Claude Haiku 3.5
VisionToolsCache
Anthropic$0.800$4.00200K
Qwen Qwen3 Coder 480B A35b Instruct MaasQwen$1.00$4.00262K
Claude 3.5 HaikuAnthropic$1.00$5.00200K
Claude Haiku 4.5
VisionReasoningToolsCache
Anthropic$1.00$5.00200K
DeepSeek Ai DeepSeek R1 0528 MaasDeepSeek$1.35$5.4065K
DeepSeek Ai DeepSeek V3.1 MaasDeepSeek$1.35$5.40164K
Mistral Large 2407Mistral$2.00$6.00128K
Mistral Large 2411Mistral$2.00$6.00128K
Mistral Large 2411 001Mistral$2.00$6.00128K
Mistral Large LatestMistral$2.00$6.00128K
Xai Grok 4.20 Non ReasoningGoogle$2.00$6.002.0M
Xai Grok 4.20 ReasoningGoogle$2.00$6.002.0M
Gemini 3.5 Flash
VisionReasoningToolsCache
Google$1.50$9.001.0M
Gemini Flash Latest
VisionReasoningToolsCache
Google$1.50$9.001.0M
Gemini Omni Flash PreviewGoogle$1.50$9.001.0M
Claude Sonnet 5
VisionReasoningToolsCache
Anthropic$2.00$10.001.0M
Gemini 2.5 Computer Use Preview 10 2025Google$1.25$10.00128K
Gemini 2.5 Pro
VisionReasoningToolsCache
Google$1.25$10.001.0M
Gemini 2.5 Pro Preview TtsGoogle$1.25$10.001.0M
Gemini 3 Pro PreviewGoogle$2.00$12.001.0M
Gemini 3.1 Pro Preview
VisionReasoningToolsCache
Google$2.00$12.001.0M
Gemini 3.1 Pro Preview Custom Tools
VisionReasoningToolsCache
Google$2.00$12.001.0M
Claude 3 SonnetAnthropic$3.00$15.00200K
Claude 3.5 SonnetAnthropic$3.00$15.00200K
Claude 3.7 Sonnet (2025-02-19)Anthropic$3.00$15.00200K
Claude Sonnet 4
VisionReasoningToolsCache
Anthropic$3.00$15.00200K
Claude Sonnet 4.5
VisionReasoningToolsCache
Anthropic$3.00$15.00200K
Claude Sonnet 4.6
VisionReasoningToolsCache
Anthropic$3.00$15.001.0M
Meta Llama 3.1 405B Instruct MaasMeta$5.00$16.00128K
Nano Banana Pro
VisionReasoning
Google$2.00$120.0066K

Frequently asked questions

How much do Anthropic Claude models cost on Google Vertex AI?

Claude models on Vertex AI range from $1.25 to $25.00 per 1 million output tokens across 19 models. Claude 3 Haiku is the cheapest; Claude Opus 4.8 is the most capable and most expensive. Input tokens cost less than output on every model.

Is Claude cheaper on Vertex AI or through the Anthropic API?

Per-token rates are effectively the same on both — Google resells Anthropic models at parity. What differs is everything around the tokens: Vertex bills through your Google Cloud account with IAM, VPC Service Controls, regional pinning and committed-use discounts, while the Anthropic API bills directly and typically ships new models first.

How much does Gemini cost on Vertex AI?

Gemini models on Vertex AI run $0.250 to $120.00 per 1 million output tokens across 52 models. The long-context models bill at a higher rate above their tier threshold, so a prompt that crosses the boundary costs more per token than the headline price.

Which models are available on Google Vertex AI?

Vertex AI hosts models from Anthropic, Google, Meta, Mistral, DeepSeek, Qwen — 102 priced models in total. Google's own Gemini family sits alongside third-party models offered as managed endpoints, all billed per token under the same Google Cloud invoice.

What is the largest context window available on Vertex AI?

Meta Llama 4 Scout 17B 128e Instruct Maas (Meta) has the largest context window on Vertex AI at 10.0M input tokens. Long context is billed the same per-token as short context on most models, but a few tier the rate above a threshold.

How do I estimate my Vertex AI bill?

Multiply input tokens by the input rate and output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Vertex also charges separately for grounding, embeddings and provisioned throughput, which are not part of the per-token rates listed here.

Head-to-head comparisons

Vertex AI pricing by vendor

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator