Skip to content
AI Model Finder
Catalog

Google

Gemini 3.7 Flash

Speed-first Gemini Flash

ReportedAugust 13, 2026 (reported)
Main purpose
High tokens-per-second chat and cheap inference
Context window
1M tokens (reported)
API pricing
$0.75 input / $3.75 output per 1M tokens introductory, doubling January 1, 2027 (reported)
Access
Gemini app, Google AI Studio, Vertex AI

Capabilities

Tags

Catalog tags plus any you add. There is no limit.

Unlimited tags. Press Enter or comma to add another — catalog tags stay, yours can be removed.

Key features

  • Very high output speed (reported)
  • 1M-token context (reported)
  • Introductory Flash pricing

Notes

  • Artificial Analysis summaries in mid-August 2026 listed Gemini 3.7 Flash first on output speed (~340 tokens/sec). Reported, not a Google quote.

Limitations

  • Introductory price is reported to rise in 2027.

Speed, price, and date from August 2026 trackers (Artificial Analysis / FelloAI).

Vendor source