Quick:
google_vertex
Active
Unknown
Gemini 3.1 Flash Lite Preview
Model Spec
google_vertex:gemini-3.1-flash-lite-preview
Modalities
Input
text
image
video
audio
pdf
Output
text
Capabilities
Chat
Reasoning
Tools
Vision
Streaming
Pricing Components
| Component | Price | Conditions | Source |
|---|---|---|---|
| token.input | $0.25 / 1M tokens | Standard | — |
| token.output | $1.50 / 1M tokens | Standard | — |
| token.cache_read | $0.03 / 1M tokens | Standard | — |
Specifications
Architecture
Unknown
Total Parameters
N/A
Active Parameters
N/A
Minimum RAM
N/A
Minimum VRAM
N/A
Context Window
1,048,576 tokens
Max Output
65,536 tokens
Input Cost
$0.25/M
Output Cost
$1.50/M
History
Raw JSONTimeline is based on collected llm_db history snapshots and may be incomplete.
2026-07-02
changed
-
extra.description
(add)
— → Low-latency Gemini model for high-volume multimodal and agent workloads
2026-06-25
changed
-
extra.status
(add)
— → deprecated
2026-06-11
changed
-
deprecated
(replace)
true → false
-
lifecycle.deprecated_at
(remove)
2026-05-12 → —
-
lifecycle.retires_at
(replace)
2026-05-25 → 2026-07-09
2026-06-10
changed
-
extra.reasoning_options
(add)
— → [1 items]
2026-05-14
changed
-
deprecated
(replace)
false → true
-
lifecycle
(replace)
— → {4 fields}
2026-05-13
changed
-
cost.cache_write
(remove)
1 → —
-
cost.input_audio
(add)
— → 0.5
2026-04-27
introduced
snapshots 64bf744 -> 6c1434b • generated 2026-08-17T11:58:52
See incorrect model data? Help us improve it.
Submit Fix on GitHub
7624
of 7758 models
1 / 153
Page 1 of 153