Context window
1,048,576 tokens
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
LLM · Google
Gemini 3.8 Flash
Google's model page lists gemini-3.8-flash with an input token limit of 1,048,576 and an output token limit of 65,536. The pricing page's paid-tier standard rate is $0.75 input and $3.75 output per 1M tokens through 31 December 2026, then $1.50 and $7.50 from 1 January 2027. The stored figures are the introductory rates. Paid tier lists Used to improve our products as No. Gemini Enterprise Agent Platform lists the same model id, gemini-3.8-flash.
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
Input price
$0.75 · Intro price until 31 Dec 2026
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/pricing
Output price
$3.75 · Intro price until 31 Dec 2026
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/pricing
API deployment
Yes
Checked 19 Oct 2026https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash
Local / self-hosted
Not published
Checked 19 Oct 2026https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash
VPC / cloud native
Yes
Checked 19 Oct 2026https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash
License
Not published
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
Data retention
Paid tier lists Used to improve our products as No. A retention period is not published on the pricing page.
Checked 19 Oct 2026https://ai.google.dev/gemini-api/docs/pricing