Google · text · last verified 2026-10-31
Gemini 3.7 Flash
Answer: As of 2026-10-31, Google lists Gemini 3.7 Flash at $0.75 input and $3.75 output per 1M tokens (cached input $0.075). Status: verified. Source: https://cloud.google.com/model-garden/pricing.
Key stats
- Input: $0.75 / 1M
- Output: $3.75 / 1M
- Cached in: $0.075
- Context: —
- Status: verified
- Last verified: 2026-10-31
- Source: official page
- Input
- $0.75 / 1M
- Output
- $3.75 / 1M
- Cached input
- $0.075
- Batch input / output
- — / —
- Long-context tier
- —
- Other pricing
- —
- Context window
- —
- Free tier
- Not stated
Listed on Google Cloud Agent Platform (Vertex AI) pricing, global endpoint; non-global endpoints $0.825/$4.125 (cached $0.0825). Introductory price through 2026-12-31; rises to $1.50 / $7.50 (cached $0.15) on 2027-01-01. Not listed on the Gemini API (ai.google.dev) pricing page as of 2026-10-31.
Cost per 1,000 tasks
- Support reply (3K/500)
- $4.13
- RAG answer (12K/700)
- $11.63
- Code review (40K/2K)
- $37.50
Cite this
Google Gemini 3.7 Flash rates from Ratecard (https://ratecardai.pages.dev/models/google-gemini-3-7-flash), checked 2026-10-31. License: CC BY 4.0. Please attribute "Ratecard" with a link to https://ratecardai.pages.dev/.
One email a week: what changed in AI API pricing, with sources. No spam; unsubscribe anytime.