Google Vertex AI models and pricing
We track 45 models on Google Vertex AI from 7 labs. The cheapest paid model is Gemini Embedding 001, at $0.15 per million input tokens and Free per million output tokens. Input prices range from $0.09 to $10 and output prices from $0.30 to $50 per million tokens. The largest context window is 2M tokens (Grok 4.20 (Reasoning) and Grok 4.20 (Non-Reasoning)). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Google Vertex AI
- Gemini Embedding 001$0.15 / Free
- Mistral Small 3.1 24B$0.10 / $0.30
- gpt-oss-120b$0.09 / $0.36
- Claude Haiku 5.5$0.10 / $0.50
- Gemma 4 26B A4B IT$0.15 / $0.60
Input / output per million tokens, paid models, by combined price.
Newest models on Google Vertex AI
- Gemini 4 Hydrogen12 Nov 2026
- Gemini 4 Carbon10 Nov 2026
- Claude Fable 5.29 Nov 2026
- Gemini 4 Argon13 Oct 2026
- Claude Haiku 5.57 Oct 2026
By the lab's release date.
All Google Vertex AI models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Gemini 4 Hydrogen gemini-4-hydrogen | Google DeepMind | $1.50 | $7.50 | 1M | models.dev |
| Gemini 4 Carbon gemini-4-carbon | Google DeepMind | $2 | $10 | 1M | models.dev |
| Claude Fable 5.2 claude-fable-5-2@default | Anthropic | $8 | $40 | 1M | models.dev |
| Gemini 4 Argon gemini-4-argon | Google DeepMind | $2 | $10 | 1M | models.dev |
| Claude Haiku 5.5 claude-haiku-5-5@default | Anthropic | $0.10 | $0.50 | 1M | models.dev |
| Gemini Nano Banana 2.1 gemini-nano-banana-2.1 | Google DeepMind | $1.50 | $7.50 | 131K | models.dev |
| Claude Sonnet 5.5 claude-sonnet-5-5@default | Anthropic | $2 | $10 | 1M | models.dev |
| Claude Opus 5.5 claude-opus-5-5@default | Anthropic | $4 | $20 | 1M | models.dev |
| Grok 4.7 xai/grok-4.7 | xAI | $2 | $6 | 524K | models.dev |
| Gemini 3.8 Flash gemini-3.8-flash | Google DeepMind | $0.75 | $3.75 | 1M | models.dev |
| Claude Fable 5.1 claude-fable-5-1@default | Anthropic | $10 | $50 | 1M | models.dev |
| Gemini 3.7 Flash gemini-3.7-flash | Google DeepMind | $0.75 | $3.75 | 1M | models.dev |
| Grok 4.6 xai/grok-4.6 | xAI | $2 | $6 | 524K | models.dev |
| Claude Opus 5 claude-opus-5@default | Anthropic | $5 | $25 | 1M | models.dev |
| Gemini 3.5 Flash Lite gemini-3.5-flash-lite | Google DeepMind | $0.30 | $2.50 | 1M | models.dev |
| Nano Banana 2 Lite gemini-3.1-flash-lite-image | Google DeepMind | $0.25 | $1.50 | 66K | models.dev |
| Claude Sonnet 5 claude-sonnet-5@default | Anthropic | $2 | $10 | 1M | models.dev |
| GLM-5.2 zai-org/glm-5.2-maas | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| Claude Fable 5 claude-fable-5@default | Anthropic | $10 | $50 | 1M | models.dev |
| Nano Banana Pro gemini-3-pro-image | Google DeepMind | $2 | $12 | 66K | models.dev |
| Claude Opus 4.8 claude-opus-4-8@default | Anthropic | $5 | $25 | 1M | models.dev |
| Nano Banana 2 gemini-3.1-flash-image | Google DeepMind | $0.50 | $3 | 131K | models.dev |
| Gemini 3.5 Flash gemini-3.5-flash | Google DeepMind | $1.50 | $9 | 1M | models.dev |
| Gemini 3.1 Flash Lite gemini-3.1-flash-lite | Google DeepMind | $0.25 | $1.50 | 1M | models.dev |
| Grok 4.3 xai/grok-4.3 | xAI | $1.25 | $2.50 | 200K | models.dev |
| Claude Opus 4.7 claude-opus-4-7@default | Anthropic | $5 | $25 | 1M | models.dev |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it-maas | Google DeepMind | $0.15 | $0.60 | 262K | models.dev |
| Grok 4.20 (Reasoning) xai/grok-4.20-reasoning | xAI | $1.25 | $2.50 | 2M | models.dev |
| Grok 4.20 (Non-Reasoning) xai/grok-4.20-non-reasoning | xAI | $1.25 | $2.50 | 2M | models.dev |
| Gemini 3.1 Pro Preview Custom Tools gemini-3.1-pro-preview-customtools | Google DeepMind | $2 | $12 | 1M | models.dev |
| Gemini Pro Latest gemini-3.1-pro-preview | Google DeepMind | $2 | $12 | 1M | models.dev |
| Claude Sonnet 4.6 claude-sonnet-4-6@default | Anthropic | $3 | $15 | 1M | models.dev |
| Claude Opus 4.6 claude-opus-4-6@default | Anthropic | $5 | $25 | 1M | models.dev |
| Gemini 3 Flash Preview gemini-3-flash-preview | Google DeepMind | $0.50 | $3 | 1M | models.dev |
| Claude Opus 4.5 claude-opus-4-5@20251101 | Anthropic | $5 | $25 | 200K | models.dev |
| Claude Haiku 4.5 claude-haiku-4-5@20251001 | Anthropic | $1 | $5 | 200K | models.dev |
| Gemini 2.5 Pro TTS gemini-2.5-pro-tts | Google DeepMind | $1 | $20 | 33K | models.dev |
| Gemini 2.5 Flash TTS gemini-2.5-flash-tts | Google DeepMind | $0.50 | $10 | 33K | models.dev |
| Nano Banana gemini-2.5-flash-image | Google DeepMind | $0.30 | $2.50 | 33K | models.dev |
| gpt-oss-120b openai/gpt-oss-120b-maas | OpenAI | $0.09 | $0.36 | 131K | models.dev |
| Codestral 25.08 codestral-2 | Mistral AI | $0.30 | $0.90 | 128K | models.dev |
| Gemini Embedding 001 gemini-embedding-001 | Google DeepMind | $0.15 | Free | 2K | models.dev |
| Mistral Medium 3 mistral-medium-3 | Mistral AI | $0.40 | $2 | 131K | models.dev |
| Llama-4-Scout-17B-16E-Instruct-FP8 meta/llama-4-scout-17b-16e-instruct-maas | Meta | $0.25 | $0.70 | 1.3M | models.dev |
| Mistral Small 3.1 24B mistral-small-2503 | Mistral AI | $0.10 | $0.30 | 128K | models.dev |
Frequently asked questions
How much does Google Vertex AI cost per million tokens?
Prices on Google Vertex AI depend on the model. Across the 45 models we track, input costs $0.09 to $10 per million tokens and output costs $0.30 to $50 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on Google Vertex AI?
Gemini Embedding 001 from Google DeepMind is the cheapest paid model we track on Google Vertex AI, at $0.15 per million input tokens and Free per million output tokens. Next are Mistral Small 3.1 24B ($0.10 / $0.30) and gpt-oss-120b ($0.09 / $0.36). Prices last verified 18 Nov 2026.
How many models does Google Vertex AI offer?
We currently track 45 active models on Google Vertex AI from 7 labs, led by Google DeepMind (20), Anthropic (14), xAI (5) and Mistral AI (3).
Which model on Google Vertex AI has the largest context window?
Grok 4.20 (Reasoning) and Grok 4.20 (Non-Reasoning) share the largest context window we track on Google Vertex AI: 2,000,000 tokens (2M).