Model Overview
Gemini 1.5 Flash-8B is a smaller model designed for high volume and lower intelligence tasks with cost efficiency.
Key Features
- Medium intelligence (2/4 dots rating)
- Very fast speed (5/5 lightning bolts rating)
- 1,048,576 context window
- 8,192 max output tokens
- Knowledge cutoff not specified
- Audio, images, video, and text input support
- Text output support
Technical Specifications
- Model Code: gemini-1.5-flash-8b
- Supports: Input: audio, images, video, text; Output: text only
- Features: System instructions, JSON mode, JSON schema, adjustable safety settings, caching, tuning, function calling, code execution
- Audio/Visual Specs: Max 3,600 images per prompt, 1 hour video, ~9.5 hours audio
- Pricing:
- Input: $0.0375 per 1M tokens (≤128k prompts), $0.075 per 1M tokens (>128k prompts)
- Output: $0.15 per 1M tokens (≤128k prompts), $0.30 per 1M tokens (>128k prompts)
- Context caching: $0.01 per 1M tokens (≤128k), $0.02 per 1M tokens (>128k), $0.25 per hour storage
- Free Tier: Available
Snapshots
- gemini-1.5-flash-8b (latest stable)
- gemini-1.5-flash-8b-latest
- gemini-1.5-flash-8b-001 (stable)
Positioning and Use Cases
Optimized for high volume and lower intelligence tasks. Most cost-effective option for simple tasks that don't require advanced reasoning.
Rate Limits
- Standard rate limits apply
Documentation
Official Documentation
