vertex/gemini-3.5-flash
Gemini 3.5 Flash is a foundational Flash model for routine, high-throughput workloads. It is suitable for text generation, summarization, classification, translation, question answering, and basic coding assistance. The model emphasizes stable speed and general performance, while supporting multimodal inputs, common tool calls, and structured outputs for large-scale automation.
- Context
- 1048576 tokens
- Max output
- 65536 tokens
- Input
- llm image video text-to-speech
- Output
- llm
Pricing
Input: $0.3 / 1M tokens
Output: $2.4999999999999 / 1M tokens
Cached input: $0.03 / 1M tokens
Endpoints
- gemini
- openai