Gemini 3.5 Flash

Recommended

gemini-3.5-flash · Gemini · text

Back to Models Back to Docs

Platform

Google Gemini

Visit Official Site

API Pricing

Input / 1M

$1.5/M$1.05/M30% OFF

Output / 1M

$9/M$6.3/M30% OFF

Cache Read / 1M

$0.15/M$0.105/M30% OFF

Overview

Gemini 3.5 Flash is Google DeepMind's ultra-fast model, offering 1M context with low latency and excellent value. It supports implicit caching, visual understanding, and Function Call. Ideal for high-concurrency, low-latency scenarios: customer support, classification, summarization, and lightweight code completion.

Capabilities

1M context; implicit caching (cache_read 25% of input); visual understanding; Function Call; JSON mode; fast responses.

Use Cases

High-concurrency customer support; classification and tagging; summarization; lightweight code completion; image recognition; video content understanding.

Limitations

Does not generate images; implicit caching is not a guaranteed hit; prices double when context exceeds 128k; max_tokens capped at 8K.

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="gemini-3.5-flash"
claude

Context Window

1M ctx

Thinking Mode

Not supported

Overview

Gemini 3.5 Flash, with a 1M context window and 64K output. Balances speed and quality, well suited for general production tasks.