Gemini 3.8 Live

Try in Agent Studio Pricing

Model ID	gemini-3.8-live
Modalities	description Text Input and output photo Image Input only mic Audio Input and output videocam Video Input and output
Token limits	Maximum input tokens	128K
	Maximum output tokens	64K
Capabilities	Thinking Not supported System instructions Supported Structured output Not supported Context caching Not supported RAG Engine Not supported Tuning Not supported Agentic video understanding Not supported
Tools	Grounding Google Search Supported Code execution Not supported Function calling Supported URL context Not supported Computer use Preview feature Not supported
APIs	GenerateContent API Supported Interactions API Preview feature Not supported Gemini Live API Supported Count Tokens API Not supported Chat Completions API Not supported
Consumption options	Provisioned Throughput Supported Batch inference Not supported Pay-as-you-go Standard PayGo Supported Fixed quota Not supported
Technical specifications	Text	Supported MIME types: text/plain
	Image	Standard input resolution: 768 x 768 Minimum custom avatar reference image resolution: 704 x 1280 (portrait) or 1280 x 704 (landscape) Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Audio	Maximum number of audio files per prompt: 1-stream Required audio input format: Raw 16-bit PCM audio at 16kHz, little-endian Required audio output format: Raw 16-bit PCM audio at 24kHz, little-endian Supported MIME types: audio/x-aac, audio/flac, audio/mp3, audio/m4a, audio/mpeg, audio/mpga, audio/mp4, audio/ogg, audio/pcm, audio/wav, audio/webm, audio/mpa
	Video	Standard input resolution: 768 x 768 (1 FPS) Minimum Live Avatar output resolution: 704 x 1280 (portrait) or 1280 x 704 (landscape) at 24 FPS Supported MIME types: video/x-flv, video/quicktime, video/mpeg, video/mpegs, video/mpg, video/mp4, video/webm, video/wmv, video/3gpp
Supported regions	Model availability	Multi-region: us, eu United States: us-central1
	ML processing	Multi-region: us, eu
	Provisioned Throughput	Multi-region: us, eu United States: us-central1
	Standard PayGo	Multi-region: us, eu United States: us-central1
Knowledge cutoff date	January 2025
Versions	gemini-3.8-live Launch stage: GA Release date: September 24, 2026 Retirement date^†: September 25, 2027 or later
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	See Security controls for more information.

^† Listed retirement dates refer to retirement of support in Gemini Enterprise Agent Platform. Models may remain accessible through the Gemini API after these dates have passed. The Gemini API is not a Google Cloud offering and is subject to its own terms of service. For details, see the Gemini API documentation.