Google Vertex AI pricing & review
Gemini plus 100+ models in Google Cloud's ML platform, with enterprise governance, grounding and tuning pipelines.
Where Google Vertex AI wins
- Enterprise governance
- Grounding with Google Search
- Model Garden variety
Google Vertex AI model pricing
List prices refreshed 2026-10-08 ยท cheapest 25 shown| Model | Input $/1M | Output $/1M | Market floor in |
|---|---|---|---|
| GPT-OSS 20B | $0.070 | $0.250 | $0.015at Darkbloom |
| GPT-OSS 120B | $0.090 | $0.360 | $0.030at W&B Inference |
| Mistral Small 4 | $0.100 | $0.300 | $0.100at Mistral AI |
| Claude Haiku 5.5 | $0.100 | $0.500 | $0.100at OpenRouter |
| Gemini 2.5 Flash Lite | $0.100 | $0.400 | $0.075at Oracle OCI |
| Qwen3 Next 80B A3B Instruct | $0.150 | $1.20 | $0.090at DeepInfra |
| Qwen3 Next 80B A3B Thinking | $0.150 | $1.20 | $0.140at DeepInfra |
| Gemma 4 26B A4B | $0.150 | $0.600 | $0.070at DeepInfra |
| Codestral 2508 | $0.200 | $0.600 | $0.200at Google Vertex AI |
| Jamba-1.5-Mini | $0.200 | $0.400 | $0.200at AWS Bedrock |
| Grok-4-1-Fast-Non-Reasoning | $0.200 | $0.500 | $0.200at Azure AI Foundry |
| Grok-4-1-Fast-Reasoning | $0.200 | $0.500 | $0.200at Azure AI Foundry |
| Jamba-1.5 | $0.200 | $0.400 | $0.200at AI21 Labs |
| Jamba-1.5-Mini@001 | $0.200 | $0.400 | $0.200at AI21 Labs |
| Qwen3 235B A22B | $0.220 | $0.880 | $0.180at DeepInfra |
| Qwen3-Coder-480b-A35b-Instruct | $0.220 | $1.80 | $0.220at Google Vertex AI |
| Llama 4 Scout | $0.250 | $0.700 | $0.050at Lambda |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | $0.250at Google Vertex AI |
| Claude-3-Haiku | $0.250 | $1.25 | $0.250at OpenRouter |
| Gemini 2.5 Flash | $0.300 | $2.50 | $0.150at Oracle OCI |
| Gemini 3.5 Flash Lite | $0.300 | $2.50 | $0.300at Google Vertex AI |
| Llama 4 Maverick | $0.350 | $1.15 | $0.050at Lambda |
| Mistral Medium 3 | $0.400 | $2.00 | $0.400at Google Vertex AI |
| Gemini 3 Flash Preview | $0.500 | $3.00 | $0.500at Google Vertex AI |
| DeepSeek V3.2 | $0.560 | $1.68 | $0.260at DeepInfra |