Skip to main content
GOGoogle/ Gemini

Gemini 3.1 Flash Lite Preview

google/gemini-3.1-flash-lite-preview

Low-latency Gemini model for high-volume multimodal and agent workloads

Model information

Released
2026-03-03
Context window
1M
Max output
66K
Weights
Closed

Modalities

Input
AudioDocumentImageTextVideo
Output
Text

Identity

Version
gemini-3.1-flash-lite-preview
Knowledge cutoff
2025-01
Aliases
Gemini 3.1 Flash Lite Preview

Capabilities

AttachmentsReasoningStructuredTemperatureTool call

Official price

input $0.25/M · output $1.5/M
cache read $0.025/M

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
Vivgridgemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M · cache write $1/M
Yes
Googlegemini-3.1-flash-lite-previewgoogle_generate_content1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M
Yes
ZenMuxgoogle/gemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsTool callTemperature
-
input $0.25/M · output $1.5/M
Yes
Abacusgemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M · cache write $1/M
Yes
OrcaRoutergoogle/gemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M
Yes
Vertexgemini-3.1-flash-lite-previewcustom1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M
Yes
Kilo Gatewaygoogle/gemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M · cache write $0.083/M
Yes
Merge Gatewaygoogle/gemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
-
input $0.25/M · output $1.5/M
cache read $0.025/M
Yes
OpenRoutergoogle/gemini-3.1-flash-lite-previewopenai_chat1M66K
AttachmentsReasoningTool callStructuredTemperature
Reasoning levels: high, medium, low, minimal, Default reasoning: minimal
input $0.25/M · output $1.5/M
cache read $0.025/M · cache write $0.083/M
Yes

FAQ