Gemini 3.5 Flash

Provider: Google AI US Official API price

Input price
$0.75
/ 1M tokens
Output price
$4.50
/ 1M tokens
Cache price
$0.075
/ 1M tokens (read)
Batch API
$0.75 / $4.50
input / output per 1M tokens
Context
1.05M tokens
Max output 66K tokens

Overview

Google's high-efficiency multimodal model targets parallel agentic execution, coding, and reasoning workloads. It occupies a mid-tier position with a 1M token context window.

Strengths

  • Processes 1,048,576 tokens of context
  • Outputs up to 65,536 tokens
  • Supports vision, audio, and thinking
  • Cached input drops to $0.075 per million tokens

Best use cases

  • Parallel agentic execution tasks
  • Long-context document analysis
  • Multimodal data extraction pipelines
  • High-speed coding workflows

Pricing position

Input costs $0.75 and output costs $4.50 per million tokens, making output significantly pricier than DeepSeek V4 Pro at $1.98 or Mistral Large 4 at $2.10.

Caveats

No free tier is available. Cheaper sibling Gemini 3.1 Flash Lite charges $0.125 input and $0.75 output.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
66K tokens
Knowledge cutoff
2025-01-01
Listed on OpenRouter
2026-05-19
Tracked since
2026-05-19
Last updated
2026-11-10

Features

Image inputAudioFunction callingJSON outputReasoning

Price history

  • 2026-05-19 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.30
1M (small app) 1 0.5 $3.00
10M (mid scale) 10 5 $30.00
100M (large) 100 50 $300.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemini-3.5-flash)