Back to models
available

Gemini 3.1 Flash Lite (Vertex AI, US)

google/gemini-3-1-flash-lite@us

Prices

Input

$0.25 per 1M tokens

low
Input (audio tokens)

$0.55 per 1M tokens

low
Input (audio)

$0.50 per 1M tokens

low
Input (cache write)

$0.0833 per 1M tokens

low
Input (cache write) (region: us)

$0.0917 per 1M tokens

low
Input (cached read)

$0.025 per 1M tokens

low
Input (cached read) (region: us)

$0.0275 per 1M tokens

low
Input (region: us)

$0.275 per 1M tokens

low
Output

$1.50 per 1M tokens

low
Output (reasoning) (kind: reasoning, region: us)

$1.65 per 1M tokens

low
Output (reasoning) (kind: reasoning)

$1.50 per 1M tokens

low
Output (region: us)

$1.65 per 1M tokens

low

Specifications

Provider
google
Context window
1,048,576
Max output tokens
65,536
Open weights
no
Released
05/07/2026
Retires
no date announced
First seen by this tracker

Price history

Input (region: us) — per 1M tokens

0.275010/19/2026today
Recorded changes for Input (region: us)
FromAmount
10/19/20260.25
11/14/20260.275

Output (region: us) — per 1M tokens

1.65010/19/2026today
Recorded changes for Output (region: us)
FromAmount
10/19/20261.5
11/14/20261.65

Input (cached read) (region: us) — per 1M tokens

0.0275010/19/2026today
Recorded changes for Input (cached read) (region: us)
FromAmount
10/19/20260.025
11/14/20260.0275

Input (cache write) (region: us) — per 1M tokens

0.0917010/19/2026today
Recorded changes for Input (cache write) (region: us)
FromAmount
10/19/20260.0833
11/14/20260.0917

Output (reasoning) (kind: reasoning, region: us) — per 1M tokens

1.65010/19/2026today
Recorded changes for Output (reasoning) (kind: reasoning, region: us)
FromAmount
10/19/20261.5
11/14/20261.65

Input (audio tokens) — per 1M tokens

0.55010/19/2026today
Recorded changes for Input (audio tokens)
FromAmount
10/19/20260.5
11/14/20260.55

No changes recorded

Input
0.25 per 1M tokens, unchanged since 09/14/2026
Output
1.5 per 1M tokens, unchanged since 09/14/2026
Input (cached read)
0.025 per 1M tokens, unchanged since 09/14/2026
Input (cache write)
0.0833 per 1M tokens, unchanged since 09/14/2026
Output (reasoning) (kind: reasoning)
1.5 per 1M tokens, unchanged since 09/14/2026
Input (audio)
0.5 per 1M tokens, unchanged since 09/14/2026

Last updated 11/16/2026, 01:12