Google Vertex AI models & pricing

Google Vertex AI hosts 210 models (183 with public pricing) covering 10 modalities. Enterprise GCP endpoint for Gemini, Anthropic, Meta, and Mistral models with VPC-SC and IAM. Cheapest input starts at $0.004688/M tokens; the most premium goes up to $15.00/M. Use Future AGI's Agent Command Center to route any Google Vertex AI model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗
210

chat 148

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Gemini 1.5 Flash exp 0827 Deprecated $0.004688/M $0.004688/M $0.004688/M 1,000,000 tools · vision
Gemini 1.5 Flash Deprecated $0.0750/M $0.300/M $0.131/M 1,000,000 tools · vision
Gemini 1.5 Flash 001 Deprecated $0.0750/M $0.300/M $0.131/M 1,000,000 tools · vision
Gemini 1.5 Flash 002 Deprecated $0.0750/M $0.300/M $0.131/M 1,048,576 tools · vision
Gemini 1.5 Flash preview 0514 Deprecated $0.0750/M $0.004688/M $0.0574/M 1,000,000 tools · vision
Gemini 2.0 Flash Lite Deprecated $0.0750/M $0.300/M $0.131/M 1,048,576 tools · vision · cache
Gemini 2.0 Flash Lite 001 Deprecated $0.0750/M $0.300/M $0.131/M 1,048,576 tools · vision · cache
Gemini 1.5 Pro preview 0215 Deprecated $0.0781/M $0.313/M $0.137/M 1,000,000 tools
Gemini 1.5 Pro preview 0409 Deprecated $0.0781/M $0.313/M $0.137/M 1,000,000 tools
Gemini 1.5 Pro preview 0514 Deprecated $0.0781/M $0.313/M $0.137/M 1,000,000 tools
Gemini 2.0 Flash Deprecated $0.1000/M $0.400/M $0.175/M 1,048,576 tools · vision · audio · cache
Gemini 2.0 Flash preview Image Generation Deprecated $0.1000/M $0.400/M $0.175/M 1,048,576 tools · vision · audio · cache
Gemini 2.5 Flash Lite $0.1000/M $0.400/M $0.175/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Flash Lite preview 06.17 Deprecated $0.1000/M $0.400/M $0.175/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Flash Lite preview 09.2025 $0.1000/M $0.400/M $0.175/M 1,048,576 tools · vision · reasoning · cache
Chat Bison $0.125/M $0.125/M $0.125/M 8,192
Chat Bison 001 $0.125/M $0.125/M $0.125/M 8,192
Chat Bison 002 Deprecated $0.125/M $0.125/M $0.125/M 8,192
Chat Bison 32k $0.125/M $0.125/M $0.125/M 32,000
Chat Bison 32k 002 $0.125/M $0.125/M $0.125/M 32,000
Code Bison $0.125/M $0.125/M $0.125/M 6,144
Codechat Bison $0.125/M $0.125/M $0.125/M 6,144
Codechat Bison 001 $0.125/M $0.125/M $0.125/M 6,144
Codechat Bison 002 $0.125/M $0.125/M $0.125/M 6,144
Codechat Bison 32k $0.125/M $0.125/M $0.125/M 32,000
Codechat Bison 32k 002 $0.125/M $0.125/M $0.125/M 32,000
Codechat Bison latest $0.125/M $0.125/M $0.125/M 6,144
Gemini 2.0 Flash 001 Deprecated $0.150/M $0.600/M $0.262/M 1,048,576 tools · vision · cache
Gemini 2.0 Flash exp $0.150/M $0.600/M $0.262/M 1,048,576 tools · vision · cache
Gemini 2.5 Flash preview 04.17 $0.150/M $0.600/M $0.262/M 1,048,576 tools · vision · reasoning · cache
Mistral Nemo latest $0.150/M $0.150/M $0.150/M 128,000 tools
Codestral 2405 $0.200/M $0.600/M $0.300/M 128,000 tools
Codestral 2501 $0.200/M $0.600/M $0.300/M 128,000 tools
Codestral latest $0.200/M $0.600/M $0.300/M 128,000 tools
Jamba 1.5 $0.200/M $0.400/M $0.250/M 256,000
Jamba 1.5 mini $0.200/M $0.400/M $0.250/M 256,000
Jamba 1.5 mini 001 $0.200/M $0.400/M $0.250/M 256,000
Xai Grok 4.1 Fast Non Reasoning $0.200/M $0.500/M $0.275/M 2,000,000 tools · vision
Xai Grok 4.1 Fast Reasoning $0.200/M $0.500/M $0.275/M 2,000,000 tools · vision · reasoning
Claude 3 Haiku $0.250/M $1.25/M $0.500/M 200,000 tools · vision
Claude 3 Haiku (2024-03-07) $0.250/M $1.25/M $0.500/M 200,000 tools · vision
Gemini 3.1 Flash Lite $0.250/M $1.50/M $0.563/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini 3.1 Flash Lite preview $0.250/M $1.50/M $0.563/M 1,048,576 tools · vision · reasoning · audio · cache
Meta Llama 4 Scout 17B 128e Instruct Maas $0.250/M $0.700/M $0.363/M 10,000,000 tools
Meta Llama 4 Scout 17B 16e Instruct Maas $0.250/M $0.700/M $0.363/M 10,000,000 tools
Codestral 2 $0.300/M $0.900/M $0.450/M 128,000 tools
Codestral 2.001 $0.300/M $0.900/M $0.450/M 128,000 tools
Gemini 2.5 Flash $0.300/M $2.50/M $0.850/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Flash preview 05.20 Deprecated $0.300/M $2.50/M $0.850/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Flash preview 09.2025 $0.300/M $2.50/M $0.850/M 1,048,576 tools · vision · reasoning · cache
Gemini 3.5 Flash Lite $0.300/M $2.50/M $0.850/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini Robotics Er 1.5 preview $0.300/M $2.50/M $0.850/M 1,048,576 tools · vision · reasoning
Mistralai Codestral 2 $0.300/M $0.900/M $0.450/M 128,000 tools
Mistralai Codestral 2.001 $0.300/M $0.900/M $0.450/M 128,000 tools
Meta Llama 4 Maverick 17B 128e Instruct Maas $0.350/M $1.15/M $0.550/M 1,000,000 tools
Meta Llama 4 Maverick 17B 16e Instruct Maas $0.350/M $1.15/M $0.550/M 1,000,000 tools
Mistral Medium 3 $0.400/M $2.00/M $0.800/M 128,000 tools
Mistral Medium 3.001 $0.400/M $2.00/M $0.800/M 128,000 tools
Mistralai Mistral Medium 3 $0.400/M $2.00/M $0.800/M 128,000 tools
Mistralai Mistral Medium 3.001 $0.400/M $2.00/M $0.800/M 128,000 tools
Gemini 1.0 Pro $0.500/M $1.50/M $0.750/M 32,760 tools
Gemini 1.0 Pro 001 Deprecated $0.500/M $1.50/M $0.750/M 32,760 tools
Gemini 1.0 Pro 002 Deprecated $0.500/M $1.50/M $0.750/M 32,760 tools
Gemini 1.0 Pro Vision $0.500/M $1.50/M $0.750/M 16,384 tools · vision
Gemini 1.0 Pro Vision 001 Deprecated $0.500/M $1.50/M $0.750/M 16,384 tools · vision
Gemini 1.0 Ultra $0.500/M $1.50/M $0.750/M 8,192 tools
Gemini 1.0 Ultra 001 $0.500/M $1.50/M $0.750/M 8,192 tools
Gemini 2.0 Flash Live preview 04.09 $0.500/M $2.00/M $0.875/M 1,048,576 tools · vision · reasoning · cache
Gemini 3 Flash preview $0.500/M $3.00/M $1.13/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini Pro $0.500/M $1.50/M $0.750/M 32,760 tools
Gemini Pro Vision $0.500/M $1.50/M $0.750/M 16,384 tools · vision
Claude 3.5 Haiku $1.00/M $5.00/M $2.00/M 200,000 tools
Claude 3.5 Haiku (2024-10-22) $1.00/M $5.00/M $2.00/M 200,000 tools
Claude Haiku 4.5 $1.00/M $5.00/M $2.00/M 200,000 tools · vision · reasoning · cache
Claude Haiku 4.5 (2025-10-01) $1.00/M $5.00/M $2.00/M 200,000 tools · vision · reasoning · cache
Mistral Small 2503 $1.00/M $3.00/M $1.50/M 128,000 tools · vision
Mistral Small 2503.001 $1.00/M $3.00/M $1.50/M 32,000 tools
Gemini 1.5 Pro Deprecated $1.25/M $5.00/M $2.19/M 2,097,152 tools · vision
Gemini 1.5 Pro 001 Deprecated $1.25/M $5.00/M $2.19/M 1,000,000 tools · vision
Gemini 1.5 Pro 002 Deprecated $1.25/M $5.00/M $2.19/M 2,097,152 tools · vision
Gemini 2.0 Pro exp 02.05 $1.25/M $10.00/M $3.44/M 2,097,152 tools · vision · audio · cache
Gemini 2.5 Computer Use preview 10.2025 $1.25/M $10.00/M $3.44/M 128,000 tools · vision
Gemini 2.5 Pro $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini 2.5 Pro exp 03.25 $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · audio · cache
Gemini 2.5 Pro preview 03.25 Deprecated $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Pro preview 05.06 Deprecated $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Pro preview 06.05 $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · reasoning · cache
Gemini 2.5 Pro preview TTS $1.25/M $10.00/M $3.44/M 1,048,576 tools · vision · cache
Gemini 3.5 Flash $1.50/M $9.00/M $3.38/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini 3.6 Flash $1.50/M $7.50/M $3.00/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini Omni Flash preview $1.50/M $9.00/M $3.38/M 1,048,576 vision · reasoning · audio
Claude Sonnet 5 $2.00/M $10.00/M $4.00/M 1,000,000 tools · vision · reasoning · cache
Claude Sonnet 5 Default $2.00/M $10.00/M $4.00/M 1,000,000 tools · vision · reasoning · cache
Gemini 3.1 Pro preview $2.00/M $12.00/M $4.50/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini 3.1 Pro preview Customtools $2.00/M $12.00/M $4.50/M 1,048,576 tools · vision · reasoning · audio · cache
Gemini 3 Pro Preview Deprecated $2.00/M $12.00/M $4.50/M 1,048,576 tools · vision · reasoning · audio · cache
Jamba 1.5 Large $2.00/M $8.00/M $3.50/M 256,000
Jamba 1.5 Large 001 $2.00/M $8.00/M $3.50/M 256,000
Mistral Large 2407 $2.00/M $6.00/M $3.00/M 128,000 tools
Mistral Large 2411 $2.00/M $6.00/M $3.00/M 128,000 tools
Mistral Large 2411.001 $2.00/M $6.00/M $3.00/M 128,000 tools
Mistral Large latest $2.00/M $6.00/M $3.00/M 128,000 tools
Xai Grok 4.20 Non Reasoning $2.00/M $6.00/M $3.00/M 2,000,000 tools · vision
Xai Grok 4.20 Reasoning $2.00/M $6.00/M $3.00/M 2,000,000 tools · vision · reasoning
Claude 3.5 Sonnet $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude 3.5 Sonnet (2024-06-20) $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude 3.5 Sonnet v2 $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude 3.5 Sonnet v2 (2024-10-22) $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude 3.7 Sonnet (2025-02-19) Deprecated $3.00/M $15.00/M $6.00/M 200,000 tools · vision · reasoning · cache
Claude 3 Sonnet $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude 3 Sonnet (2024-02-29) $3.00/M $15.00/M $6.00/M 200,000 tools · vision
Claude Sonnet 4 $3.00/M $15.00/M $6.00/M 1,000,000 tools · vision · reasoning · cache
Claude Sonnet 4 (2025-05-14) $3.00/M $15.00/M $6.00/M 1,000,000 tools · vision · reasoning · cache
Claude Sonnet 4.5 $3.00/M $15.00/M $6.00/M 200,000 tools · vision · reasoning · cache
Claude Sonnet 4.5 (2025-09-29) $3.00/M $15.00/M $6.00/M 200,000 tools · vision · reasoning · cache
Claude Sonnet 4.6 $3.00/M $15.00/M $6.00/M 1,000,000 tools · vision · reasoning · cache
Claude Sonnet 4.6 Default $3.00/M $15.00/M $6.00/M 1,000,000 tools · vision · reasoning · cache
Mistral Nemo 2407 $3.00/M $3.00/M $3.00/M 128,000 tools
Claude Opus 4.5 $5.00/M $25.00/M $10.00/M 200,000 tools · vision · reasoning · cache
Claude Opus 4.5 (2025-11-01) $5.00/M $25.00/M $10.00/M 200,000 tools · vision · reasoning · cache
Claude Opus 4.6 $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 4.6 Default $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 4.7 $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 4.7 Default $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 4.8 $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 4.8 Default $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 5 $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Claude Opus 5 Default $5.00/M $25.00/M $10.00/M 1,000,000 tools · vision · reasoning · cache
Meta Llama 3.1 405B Instruct Maas $5.00/M $16.00/M $7.75/M 128,000 vision
Claude Fable 5 $10.00/M $50.00/M $20.00/M 1,000,000 tools · vision · reasoning · cache
Claude Fable 5 Default $10.00/M $50.00/M $20.00/M 1,000,000 tools · vision · reasoning · cache
Claude 3 Opus $15.00/M $75.00/M $30.00/M 200,000 tools · vision
Claude 3 Opus (2024-02-29) $15.00/M $75.00/M $30.00/M 200,000 tools · vision
Claude Opus 4 $15.00/M $75.00/M $30.00/M 200,000 tools · vision · reasoning · cache
Claude Opus 4.1 $15.00/M $75.00/M $30.00/M 200,000 tools · vision
Claude Opus 4.1 (2025-08-05) $15.00/M $75.00/M $30.00/M 200,000 tools · vision
Claude Opus 4 (2025-05-14) $15.00/M $75.00/M $30.00/M 200,000 tools · vision · reasoning · cache
Gemini 2.0 Flash Thinking exp Deprecated — — — 1,048,576 tools · vision · cache
Gemini 2.0 Flash Thinking exp 01.21 Deprecated — — — 1,048,576 vision · reasoning · cache
Gemini Pro Experimental — — — 1,000,000
Medlm Large — — — 8,192
Medlm Medium — — — 32,768
Meta Llama 3.1 70B Instruct Maas — — — 128,000 vision
Meta Llama 3.1 8B Instruct Maas — — — 128,000 vision
Meta Llama 3.2 90B Vision Instruct Maas — — — 128,000 vision
Meta Llama3.405b Instruct Maas — — — 32,000
Meta Llama3.70b Instruct Maas — — — 32,000
Meta Llama3.8b Instruct Maas — — — 32,000

embedding 17

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Text Embedding preview 0409 $0.006250/M — — 3,072
Text Multilingual Embedding preview 0409 $0.006250/M — — 3,072
Text Embedding 004 Deprecated $0.1000/M — — 2,048
Text Embedding 005 $0.1000/M — — 2,048
Text Embedding Large exp 03.07 $0.1000/M — — 8,192
Text Multilingual Embedding 002 $0.1000/M — — 2,048
Textembedding Gecko $0.1000/M — — 3,072
Textembedding Gecko 001 $0.1000/M — — 3,072
Textembedding Gecko 003 $0.1000/M — — 3,072
Textembedding Gecko Multilingual $0.1000/M — — 3,072
Textembedding Gecko Multilingual 001 $0.1000/M — — 3,072
Gemini Embedding 001 $0.150/M — — 2,048
Gemini Embedding 2 $0.200/M — — 8,192
Gemini Embedding 2 preview $0.200/M — — 8,192
Multimodalembedding $0.800/M — — 2,048
Multimodalembedding 001 $0.800/M — — 2,048
Gemini Flash Experimental — — — 1,000,000

completion 15

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Code Bison 001 $0.125/M $0.125/M $0.125/M 6,144
Code Bison 002 $0.125/M $0.125/M $0.125/M 6,144
Code Bison 32k 002 $0.125/M $0.125/M $0.125/M 6,144
Code Bison32k $0.125/M $0.125/M $0.125/M 6,144
Code Gecko $0.125/M $0.125/M $0.125/M 2,048
Code Gecko 001 $0.125/M $0.125/M $0.125/M 2,048
Code Gecko 002 $0.125/M $0.125/M $0.125/M 2,048
Code Gecko latest $0.125/M $0.125/M $0.125/M 2,048
Text Bison32k $0.125/M $0.125/M $0.125/M 8,192
Text Bison32k 002 $0.125/M $0.125/M $0.125/M 8,192
Text Unicorn $10.00/M $28.00/M $14.50/M 8,192
Text Unicorn 001 $10.00/M $28.00/M $14.50/M 8,192
Text Bison — — — 8,192
Text Bison 001 — — — 8,192
Text Bison 002 — — — 8,192

image generation 15

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Gemini 2.5 Flash Image $0.300/M $2.50/M $0.850/M 32,768 tools · vision · cache
Gemini 2.5 Flash Image preview Deprecated $0.300/M $30.00/M $7.73/M 1,048,576 tools · vision · cache
Gemini 3.1 Flash Image $0.500/M $3.00/M $1.13/M 65,536 vision · cache
Gemini 3.1 Flash Image preview $0.500/M $3.00/M $1.13/M 65,536 vision · cache
Deep Research Pro preview 12.2025 $2.00/M $12.00/M $4.50/M 65,536 vision · cache
Gemini 3 Pro Image $2.00/M $12.00/M $4.50/M 65,536 vision · cache
Gemini 3 Pro Image preview $2.00/M $12.00/M $4.50/M 65,536 vision · cache
Imagegeneration 006 — — — —
Imagen 3.0 Capability 001 — — — —
Imagen 3.0 Fast Generate 001 — — — —
Imagen 3.0 Generate 001 — — — —
Imagen 3.0 Generate 002 Deprecated — — — —
Imagen 4.0 Fast Generate 001 — — — —
Imagen 4.0 Generate 001 — — — —
Imagen 4.0 Ultra Generate 001 — — — —

video generation 9

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Veo 2.0 Generate 001 — — — 1,024
Veo 3.0 Fast Generate 001 — — — 1,024
Veo 3.0 Fast Generate preview Deprecated — — — 1,024
Veo 3.0 Generate 001 — — — 1,024
Veo 3.0 Generate preview Deprecated — — — 1,024
Veo 3.1 Fast Generate 001 — — — 1,024
Veo 3.1 Fast Generate preview — — — 1,024
Veo 3.1 Generate 001 — — — 1,024
Veo 3.1 Generate preview — — — 1,024

ocr 2

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
DeepSeek AI DeepSeek OCR Maas $0.300/M $1.20/M $0.525/M —
Mistral OCR 2505 — — — —

audio speech 1

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Chirp — — — —

audio transcription 1

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Chirp 3 — — — —

realtime 1

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Gemini Live 2.5 Flash preview Native Audio 09.2025 $0.300/M $2.00/M $0.725/M 1,048,576 tools · vision · audio · cache

vector store 1

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Search API — — — —

FAQ

How many Google Vertex AI models are there?

210 Google Vertex AI models are listed across 10 modalities on this page. 183 have public per-token pricing.

How is Google Vertex AI pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which Google Vertex AI model is cheapest?

Input pricing on Google Vertex AI starts at $0.004688 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to Google Vertex AI via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Google Vertex AI target, and call Google Vertex AI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any Google Vertex AI model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.