API model
Gemini 3.5 Flash
Google · Gemini · released
Google's Gemini 3.5 Flash is a fast, multimodal model with a ~1M-token context window and a dedicated thinking (reasoning) mode, priced for high-throughput use through the Gemini API.
- Context window
- 1,049K tokens
- Deployment
- Hosted API
API pricing
Per 1M tokens, standard list price.
| Provider | Input / 1M | Output / 1M | Reasoning / 1M |
|---|---|---|---|
| $1.5 | $9 | $9 |
Capabilities
- Reasoning
- Vision
- Tools / function calling
- Code
- Math
- Structured output
- Multilingual