Gemini API Pricing
Gemini models from Google Gemini API. Google's advanced AI model with multimodal capabilities. Requesty routes to 24 Google Gemini API models starting at $0.05 per 1M input tokens with context windows up to 1.0M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
gemini-3.6-flashIntelligence Index
34.0
Coding Index
69.2
GPQA Diamond
92.8%
All Google Gemini API models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 1.0M | 66K | $1.50 | $7.00 | 👁🧠🔧⚡ | 69 | |
| 1.0M | 66K | $0.38 | $1.88 | 👁🧠🔧⚡ | 69 | |
| 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 49 | |
| 1.0M | 66K | $0.15 | $1.25 | 👁🧠🔧⚡ | 49 | |
| 131K | 66K | $0.50 | $2.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 33K | $2.00 | $12.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $1.50 | $9.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $0.75 | $4.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $0.25 | $1.50 | 👁🧠🔧⚡ | 35 | |
| 1.0M | 66K | $0.13 | $0.75 | 👁🧠🔧⚡ | 35 | |
| 262K | 8K | Free | Free | 👁🧠🔧 | N/A | |
| 1.0M | 66K | $2.00 | $12.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $1.00 | $6.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $2.00 | $12.00 | 👁🧠🔧⚡ | 69 | |
| 1.0M | 66K | $1.00 | $6.00 | 👁🧠🔧⚡ | 69 | |
| 1.0M | 66K | $0.50 | $3.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $0.25 | $1.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $0.30 | $2.50 | 👁🔧⚡ | N/A | |
| 1.0M | 66K | $0.10 | $0.40 | 👁🔧⚡ | N/A | |
| 1.0M | 66K | $0.05 | $0.20 | 👁🔧⚡ | N/A | |
| 1.0M | 66K | $0.30 | $2.50 | 👁🔧⚡ | N/A | |
| 1.0M | 66K | $0.15 | $1.25 | 👁🔧⚡ | N/A | |
| 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡ | 33 | |
| 1.0M | 66K | $0.63 | $5.00 | 👁🧠🔧⚡ | 33 |
About Google Gemini API on Requesty
How many Google Gemini API models are available through Requesty?
Requesty routes to 24 Google Gemini API models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Google Gemini API model?
The cheapest Google Gemini API model starts at $0.05 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Google Gemini API pricing?
No. Requesty passes through exactly what Google Gemini API charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Google Gemini API models?
Google Gemini API's training policy varies by product and tier. See their privacy policy for specifics, and contact Requesty for enterprise-grade data controls.
Where are Google Gemini API models hosted?
Google Gemini API models are hosted in 🌍 Global. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Google Gemini API rows in the models explorer.