Gemini 3.7 Flash

Provider: Google AI US Official API price

Input price
$0.38
/ 1M tokens
Output price
$1.88
/ 1M tokens
Cache price
$0.037
/ 1M tokens (read)
Batch API
$0.38 / $1.88
input / output per 1M tokens
Context
1.05M tokens
Max output 66K tokens

Overview

Google AI's Gemini 3.7 Flash is a mid-tier reasoning and coding model built for agentic workflows and multimodal tasks.

Strengths

  • 1,048,576 token context window with 65,536 max output
  • Native support for vision, audio, and function-calling
  • Cached input drops price to $0.0375 per million tokens

Best use cases

  • Processing large multimodal documents and codebases
  • Automating multi-step agentic workflows and tool use
  • High-throughput reasoning tasks requiring JSON output

Pricing position

Input is pegged at $0.375 per million tokens, matching GPT-5.4 Mini, while output is slightly cheaper at $1.875.

Caveats

Output pricing is significantly higher than older Flash Lite variants and Gemma 3 models.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
66K tokens
Listed on OpenRouter
2026-08-13
Tracked since
2026-08-13
Last updated
2026-11-10

Features

Image inputAudioFunction callingJSON outputReasoning

Price history

  • 2026-08-13 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.13
1M (small app) 1 0.5 $1.31
10M (mid scale) 10 5 $13.13
100M (large) 100 50 $131.25

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemini-3.7-flash)