Google Vertex AI

Cloud platform · 35 models · 86 priced routes · cloud.google.com

Models on Google Vertex AI

About Google Vertex AI

BigQuery, the Gemini Enterprise Agent Platform (formerly Vertex AI), the Gemini API, Looker, AlloyDB and Spanner.

Batch: Flex/Batch tier priced at 50% of Standard in tables (e.g. Gemini 3.1 Pro input $2.00 standard vs $1.00 Flex/Batch); no explicit percentage wording

Caching: Cached input at 10% of input in tables (e.g. $2.00 vs $0.20)

Across GlyphCompany profile advisories awards 427 dated events 14 certification exams 31 certifications

Model	In / out per 1M	Vs headline
Gemini Embedding 001 us-central1 · gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding.	$0.15 / FreeSame vs headline	Same	us-central1 · gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding.
Gemini Embedding 2 us · Gemini Embedding 2 is Google's first multimodal embedding model.	$0.2 / FreeSame vs headline	Same	us · Gemini Embedding 2 is Google's first multimodal embedding model.
Gemini Embedding 2 global · Gemini Embedding 2 is Google's first multimodal embedding model.	$0.2 / FreeSame vs headline	Same	global · Gemini Embedding 2 is Google's first multimodal embedding model.
gpt-oss-120b global · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.	$0.09 / $0.36+840% vs headline	+840%	global · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
Gemini Embedding 2 eu · Gemini Embedding 2 is Google's first multimodal embedding model.	$0.22 / Free+10% vs headline	+10%	eu · Gemini Embedding 2 is Google's first multimodal embedding model.
Claude Haiku 5.5 global · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.	$0.1 / $0.5Same vs headline	Same	global · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Claude Haiku 5.5 europe · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.	$0.11 / $0.55+10% vs headline	+10%	europe · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Claude Haiku 5.5 us · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.	$0.11 / $0.55+10% vs headline	+10%	us · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Gemma 4 26B A4B global · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.	$0.15 / $0.6+209% vs headline	+209%	global · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Gemini 3.1 Flash Lite global-flex · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.	$0.125 / $0.75-50% vs headline	-50%	global-flex · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
Llama 4 Scout us-east5 · Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.	$0.25 / $0.7+202% vs headline	+202%	us-east5 · Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.
Gemini 3.5 Flash Lite global-flex · Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.	$0.15 / $1.25-50% vs headline	-50%	global-flex · Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.
DeepSeek V4.1 Flash global · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.3 / $1.2+383% vs headline	+383%	global · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
Llama 4 Maverick us-east5 · Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...	$0.35 / $1.15+81% vs headline	+81%	us-east5 · Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) global · Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.	$0.25 / $1.5Same vs headline	Same	global · Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.
Gemini 3.1 Flash Lite global · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.	$0.25 / $1.5Same vs headline	Same	global · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
Gemini 3 Flash Preview global-flex · Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.	$0.25 / $1.5-50% vs headline	-50%	global-flex · Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
Gemini 3.1 Flash Lite eu · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.	$0.275 / $1.65+10% vs headline	+10%	eu · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
Gemini 3.1 Flash Lite us · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.	$0.275 / $1.65+10% vs headline	+10%	us · Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
Llama 3.3 70B Instruct us-central1 · The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).	$0.72 / $0.72+365% vs headline	+365%	us-central1 · The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).