Gemini 3 Flash Preview
retiredGoogle · Multimodal · Released Dec 2025
Gemini 3 Flash is Google's fast, lightweight model designed for real-time applications and agentic workflows, with a 1M token context window.
- Strengths
- Delivers fast inference latency while maintaining strong reasoning capabilities across coding, multi-turn conversation, and tool use.
- Best for
- Agentic systems, chatbots, live coding assistance, and applications where throughput and response speed matter as much as reasoning quality.
- Limitations
- As a preview model, it may have stability or behavioral inconsistencies; use production-grade alternatives if reliability guarantees are critical.
Input / 1M
$0.5
Output / 1M
$3.00
Cached input / 1M
$0.05
Context window
1.05M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out decreased 0.0%
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 29 Jun 2026 | $0.5 | $3.00 | $0.05 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.5 | $3.00 | $0.05 | Imported from OpenRouter | openrouter.ai |