Vertex AI API pricing
43 Vertex AI models, in US dollars per million tokens. Updated Oct 29, 2026.
43 models
| Model | Input | Cached input | Output | Context | Notes |
|---|---|---|---|---|---|
| deep-research-pro-preview-12-2025 | $2.00 | $0.20 | $12.00 | 66K | |
| gemini-2.5-computer-use-preview-10-2025 | $1.25 | — | $10.00 | 128K | |
| gemini-2.5-flash-lite-preview-09-2025 | $0.10 | $0.01 | $0.40 | 1.05M | |
| gemini-2.5-flash-preview-09-2025 | $0.30 | $0.03 | $2.50 | 1.05M | |
| gemini-2.5-pro-preview-tts | $1.00 | $0.125 | $20.00 | 1.05M | |
| gemini-3-flash-preview | $0.50 | $0.05 | $3.00 | 1.05M | |
| gemini-3-pro-preview | $2.00 | $0.20 | $12.00 | 1.05M | |
| gemini-3.1-flash-lite | $0.25 | $0.025 | $1.50 | 1.05M | Retires May 7, 2027 |
| gemini-3.1-flash-lite-preview | $0.25 | $0.025 | $1.50 | 1.05M | |
| gemini-3.1-pro-preview | $2.00 | $0.20 | $12.00 | 1.05M | |
| gemini-3.1-pro-preview-customtools | $2.00 | $0.20 | $12.00 | 1.05M | |
| gemini-3.5-flash | $1.50 | $0.15 | $9.00 | 1.05M | Retires May 19, 2027 |
| gemini-3.5-flash-lite | $0.30 | $0.03 | $2.50 | 1.05M | Retires Jul 21, 2027 |
| gemini-3.6-flash | $1.50 | $0.15 | $7.50 | 1.05M | Retires Nov 19, 2026 |
| gemini-3.7-flash | $1.50 | $0.15 | $7.50 | 1.05M | Retires Jan 28, 2027 |
| gemini-3.8-flash | $1.50 | $0.15 | $7.50 | 1.05M | |
| gemini-3.8-flash-cyber | $1.50 | $0.15 | $7.50 | 1.05M | |
| gemini-4-argon | $2.00 | $0.10 | $10.00 | 1.05M | |
| gemini-4-argon-cyber-permissive | $4.00 | $0.20 | $20.00 | 1.05M | |
| gemini-embedding-001 | $0.15 | — | — | 2K | EmbeddingRetires May 20, 2028 |
| gemini-embedding-2 | $0.20 | — | — | 8K | Embedding |
| gemini-embedding-2-preview | $0.20 | — | — | 8K | Embedding |
| gemini-flash-experimental | $0 | — | — | 1M | Embedding |
| gemini-omni-1.1-flash | $1.50 | — | $9.00 | — | |
| gemini-omni-1.1-flash-preview | $1.50 | — | $9.00 | 58K | |
| gemini-omni-flash-preview | $1.50 | — | $9.00 | 1.05M | |
| gemini-robotics-er-1.5-preview | $0.30 | $0 | $2.50 | 1.05M | |
| gemini-robotics-er-2-preview | $1.00 | $0.10 | $5.00 | 131K | |
| gemma-4-26b-a4b-it | $0.15 | $0.015 | $0.60 | — | |
| multimodalembedding | $0.80 | — | — | 2K | Embedding |
| multimodalembedding@001 | $0.80 | — | — | 2K | EmbeddingRetires Apr 1, 2027 |
| text-embedding-004 | $0.10 | — | — | 2K | EmbeddingRetires Apr 1, 2027 |
| text-embedding-005 | $0.10 | — | — | 2K | EmbeddingRetires Apr 1, 2027 |
| text-embedding-large-exp-03-07 | $0.10 | — | — | 8K | Embedding |
| text-embedding-preview-0409 | $0.00625 | — | — | 3K | Embedding |
| text-multilingual-embedding-002 | $0.10 | — | — | 2K | EmbeddingRetires Apr 1, 2027 |
| xai/grok-4.1-fast-non-reasoning | $0.20 | $0.05 | $0.50 | 128K | |
| xai/grok-4.1-fast-reasoning | $0.20 | $0.05 | $0.50 | 128K | |
| xai/grok-4.20-non-reasoning | $1.25 | $0.20 | $2.50 | 2M | |
| xai/grok-4.20-reasoning | $1.25 | $0.20 | $2.50 | 2M | |
| xai/grok-4.3 | $1.25 | $0.20 | $2.50 | 200K | |
| xai/grok-4.6 | $2.00 | $0.50 | $6.00 | 524K | |
| xai/grok-4.7 | $2.00 | $0.50 | $6.00 | 524K |
See what your Vertex AI calls actually cost, by service, model and customer, priced for where each call ran.
Get started freeRegional endpoints: for 9 of these models, calls to a regional endpoint cost 10% more than the global price shown, where no regional price is listed. Alye applies this to each call automatically.
List prices from Vertex AI's official price list where published, otherwise LiteLLM's public price file. Long-prompt, batch and priority rates aren't shown; check Vertex AI's pricing page before you commit to a budget. All providers