Google Vertex AI API pricing
35 models · USD per 1M tokens · verified 2026-10-23
Google Vertex AI serves 35 of the models we track, 6 of them open-weights. The cheapest is Mistral Small 3.1 24B at $0.10 input and $0.30 output per million tokens. For 30 of these models, Google Vertex AI is the cheapest tracked host.
// models on Google Vertex AI
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| Mistral Small 3.1 24B BEST | Mistral | $0.10 | $0.30 | 128K | best |
| GPT OSS 120B | OpenAI | $0.09 | $0.36 | 131.1K | +124% |
| Gemini 2.5 Flash-Lite BEST | $0.10 | $0.40 | 1.05M | best | |
| Claude Haiku 5.5 BEST | Anthropic | $0.10 | $0.50 | 1M | best |
| Gemma 4 26B A4B IT | $0.15 | $0.60 | 262.1K | +90.9% | |
| Llama 4 Scout 17B | Meta | $0.25 | $0.70 | 327.7K | +141.7% |
| Codestral 25.08 BEST | Mistral | $0.30 | $0.90 | 256K | best |
| Gemini 3.1 Flash Lite BEST | $0.25 | $1.50 | 1.05M | best | |
| Gemini 3.5 Flash Lite BEST | $0.30 | $2.50 | 1.05M | best | |
| Gemini 3 Flash Preview BEST | $0.50 | $3.00 | 1.05M | best | |
| Gemini 3.6 Flash BEST | $0.75 | $3.75 | 1.05M | best | |
| Gemini 3.7 Flash BEST | $0.75 | $3.75 | 1.05M | best | |
| Gemini 3.8 Flash BEST | $0.75 | $3.75 | 1.05M | best | |
| GLM-5 | Z.AI (Zhipu) | $1.00 | $3.20 | 204.8K | best |
| Grok 4.20 (Non-Reasoning) BEST | xAI | $1.25 | $2.50 | 1M | best |
| Grok 4.20 (Reasoning) BEST | xAI | $1.25 | $2.50 | 1M | best |
| Grok 4.3 BEST | xAI | $1.25 | $2.50 | 1M | best |
| GLM-5.2 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| Grok 4.6 BEST | xAI | $2.00 | $6.00 | 500K | best |
| Grok 4.7 BEST | xAI | $2.00 | $6.00 | 500K | best |
| Gemini 3.5 Flash BEST | $1.50 | $9.00 | 1.05M | best | |
| Gemini 2.5 Pro BEST | $1.25 | $10.00 | 1.05M | best | |
| Claude Sonnet 5 BEST | Anthropic | $2.00 | $10.00 | 1M | best |
| Claude Sonnet 5.5 BEST | Anthropic | $2.00 | $10.00 | 1M | best |
| Gemini 4 Argon BEST | $2.00 | $10.00 | 1.05M | best | |
| Gemini 3.1 Pro Preview BEST | $2.00 | $12.00 | 1.05M | best | |
| Gemini 3.1 Pro Preview Custom Tools BEST | $2.00 | $12.00 | 1.05M | best | |
| Claude Sonnet 4.6 BEST | Anthropic | $3.00 | $15.00 | 1M | best |
| Claude Opus 5.5 BEST | Anthropic | $4.00 | $20.00 | 1M | best |
| Claude Opus 4.6 BEST | Anthropic | $5.00 | $25.00 | 1M | best |
| Claude Opus 4.7 BEST | Anthropic | $5.00 | $25.00 | 1M | best |
| Claude Opus 4.8 BEST | Anthropic | $5.00 | $25.00 | 1M | best |
| Claude Opus 5 BEST | Anthropic | $5.00 | $25.00 | 1M | best |
| Claude Fable 5 BEST | Anthropic | $10.00 | $50.00 | 1M | best |
| Claude Fable 5.1 BEST | Anthropic | $10.00 | $50.00 | 1M | best |
// how to read this page
Prices are Google Vertex AI's base-tier list prices per million tokens. "vs best price" compares Google Vertex AI's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.