Pricing and Models•v1.0.0•3 min read
Google Gemini API Pricing & Model Reference
Official upstream pricing, context caching, multimodal tokens, batch execution, and tool grounding rates for Google Gemini models on Valstorm.
Official Provider Documentation: Google Gemini Developer Pricing | Google AI Studio | Gemini API Documentation
Overview & Gateway Architecture
This reference document outlines the upstream provider base pricing for Google's Gemini family of models.
The Valstorm AI Platform provides unified access to Google Gemini models with full enterprise infrastructure:
- Intelligent Routing & Caching: Multi-model routing, prompt context caching, and 1M+ token window management.
- Multimodal Intelligence: Unified endpoints for text, high-resolution vision, native audio streaming, video processing, and PDF/document tokens.
- Integrated Tool Execution: Sandboxed code execution, Google Search grounding, Maps lookup, and file search integrations.
- Enterprise Controls: Unified auth, organization-level quotas, and strict multi-tenant data governance.
Note: Base provider rates shown below represent upstream pass-through pricing in USD per 1 Million (1M) tokens unless specified otherwise.
1. Gemini 3 Series (Current Generation)
All prices are in USD per 1M tokens for the Paid Tier.
| Model | Model ID | Standard Input | Standard Output (incl. Thinking) | Context Cache Read | Batch / Flex Input (50% Off) | Batch / Flex Output |
|---|---|---|---|---|---|---|
| Gemini 3.6 Flash | gemini-3.6-flash | $1.50 | $7.50 | $0.15 | $0.75 | $3.75 |
| Gemini 3.5 Flash | gemini-3.5-flash | $1.50 | $9.00 | $0.15 | $0.75 | $4.50 |
| Gemini 3.5 Flash-Lite | gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | $0.15 | $1.25 |
| Gemini 3.1 Flash-Lite | gemini-3.1-flash-lite | $0.25 (text/img) $0.50 (audio) | $1.50 | $0.025 | $0.125 (text) $0.25 (audio) | $0.75 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | $0.50 (text/img) $1.00 (audio) | $3.00 | $0.05 | $0.25 (text) $0.50 (audio) | $1.50 |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | ≤ 200k: $2.00 > 200k: $4.00 | ≤ 200k: $12.00 > 200k: $18.00 | $0.20 (≤200k) $0.40 (>200k) | ≤ 200k: $1.00 > 200k: $2.00 | ≤ 200k: $6.00 > 200k: $9.00 |
2. Gemini 2.5 Series
| Model | Model ID | Standard Input | Standard Output | Context Cache Read | Batch Input | Batch Output |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | ≤ 200k: $1.25 > 200k: $2.50 | ≤ 200k: $10.00 > 200k: $15.00 | $0.125 (≤200k) $0.25 (>200k) | ≤ 200k: $0.625 > 200k: $1.25 | ≤ 200k: $5.00 > 200k: $7.50 |
| Gemini 2.5 Flash | gemini-2.5-flash | $0.30 (text/img) $1.00 (audio) | $2.50 | $0.03 (text) $0.10 (audio) | $0.15 (text) $0.50 (audio) | $1.25 |
| Gemini 2.5 Flash-Lite | gemini-2.5-flash-lite | $0.10 (text/img) $0.30 (audio) | $0.40 | $0.01 (text) | $0.05 (text) $0.15 (audio) | $0.20 |
3. Built-in Tools & Agent Extensions
| Tool / Extension | Free Quota | Paid Rate / Pricing Rules |
|---|---|---|
| Google Search Grounding | Gemini 3.x: 5,000 free requests / mo Gemini 2.5: 1,500 RPD free (Flash/Lite) | Gemini 3.x: $14.00 / 1,000 search queries Gemini 2.5: $35.00 / 1,000 grounded prompts |
| Code Execution | Included free of charge | Billed at standard model token rates for generated code and output results. |
| File Search (Retrieval) | Free tier available | Charged for vector embeddings ($0.15 / 1M tokens) + retrieved content tokens. |