Gemini 4 Hydrogen

Gemini 4 Hydrogen brings cutting-edge intelligence with speed and efficiency to everyday coding and agentic enterprise workflows.

Hydrogen is a short-term generally available (GA) release subject to a minimum 45-day retirement notice policy. For lifecycle details, see Model versions and lifecycle.

Hydrogen differs from earlier Gemini models in the following ways:

• Unified input and output token limit and long decodes: Hydrogen has a unified 1,048,576-token limit that includes both input and output tokens (where output includes thinking, function calls, and the final response) across all supported API surfaces (the GenerateContent API, the Interactions API, and the OpenAI compatibility Chat Completions API). A single foreground segment generates up to 65,536 output tokens (streaming or non-streaming). On both the Interactions API and the GenerateContent API (v1beta1), you can extend output up to 1,048,576 tokens (minus your input tokens) using long decodes: the Google Gen AI SDK and Agent Studio handle continuation_token automatically across segments, or you can use background=true on the Interactions API or pass continuation_token in a custom continuation loop (known issue: continuation_token is supported only in the v1beta1 API, which the Google Gen AI SDK uses by default). For details, see the developer's guide to Gemini 4 Hydrogen.
• Thinking levels: Hydrogen supports thinking levels LOW, MEDIUM, HIGH (default), and XHIGH. Setting thinking_budget or thinking_level="MINIMAL" returns an HTTP 400 validation error.
• Sampling parameters: Custom values for sampling parameters (temperature, top_p, and top_k) are ignored.
• Context caching: Hydrogen supports implicit caching only (4,096-token minimum), with durable caching enabled by default. Explicit context caching isn't supported. Starting on January 12, 2027, Gemini 4 Hydrogen and later models support cache control features with TTL configuration. You choose what to cache and how long cached content stays valid through TTL configuration. Cache writes are billed at 1.25x the standard input token price by default, and longer retention costs more. For details, see Pricing.
• Office and OpenDocument file inputs: In addition to PDF (application/pdf) and plain text (text/plain), Hydrogen accepts Microsoft Office (.docx, .dotx, .doc, .pptx, .ppt, .xlsx, .xls) and OpenDocument (.odt, .odp, .ods) files inline or from Cloud Storage on both the GenerateContent API and the Interactions API, including inside multimodal FunctionResponse parts.

Try in Agent Studio Deploy example app Developer guide Pricing

Note: "Deploy example app" requires a Google Cloud project with billing and Agent Platform API enabled.

Model ID	gemini-4-hydrogen
Modalities	description Text Input and output photo Image Input only mic Audio Input only videocam Video Input only
Token limits	Context window	1,048,576
	Maximum output tokens	1,048,576
Capabilities	Thinking Supported System instructions Supported Structured output Supported Context caching Implicit context caching Supported RAG Engine Not supported Tuning Not supported Agentic video understanding Supported
Tools	Grounding Google Search, Google Maps, Agent Search, Parallel Web Search, Exa Web Search, Web Grounding for Enterprise Supported Code execution Supported Function calling Supported URL context Supported Computer use Supported
APIs	GenerateContent API Supported Interactions API Supported Gemini Live API Not supported Count Tokens API Supported Chat Completions API Supported
Consumption options	Provisioned Throughput Supported Batch inference Supported Pay-as-you-go Standard PayGo with Usage Tiers, Flex PayGo, Priority PayGo Supported Fixed quota Not supported
Input size limit	GenerateContent API: 500 MiB compressed Interactions API: 256 MiB compressed (synchronous or streaming); 9.75 MiB uncompressed (deferred, when background and store are true)
Interactions API URI limit	Up to 100 distinct Cloud Storage (gs://) URIs per request across all modalities on the Interactions API, including URIs carried forward from earlier turns using previous_interaction_id. generateContent supports gs:// URIs up to the per-modality model item limits (up to 6,500 combined multimodal files when including plain-text files).
Technical specifications	Image	Maximum images per prompt: 3,000 (images and documents combined) Maximum inline part size (GenerateContent API): 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB Maximum file size per file for direct local uploads in the console: 7 MiB inline (up to 50 MiB staged to Cloud Storage) Maximum file size per file for Google Drive imports in the console: 7 MB (10 MB total) Default resolution tokens: 1,120 Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Text	Maximum number of files per prompt: 3,000 documents (shared with images; up to 6,500 total files when including plain text) Maximum number of pages per file: 3,000 Maximum inline part size (GenerateContent API): 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB Maximum file size per file for direct local uploads in the console: 7 MiB inline (up to 50 MiB staged to Cloud Storage) Maximum file size per file for Google Drive imports in the console: 7 MB (10 MB total) Default resolution tokens: 560 OCR for scanned PDFs: Not used by default Supported MIME types: application/pdf, text/plain, application/msword, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/vnd.openxmlformats-officedocument.wordprocessingml.template, application/vnd.oasis.opendocument.text, application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/vnd.oasis.opendocument.presentation, application/vnd.ms-excel, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, application/vnd.oasis.opendocument.spreadsheet
	Video	Maximum video length (with audio): Approximately 45 minutes Maximum video length (without audio): Approximately 1 hour Maximum number of videos per prompt: 10 Maximum inline part size (GenerateContent API): 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB Default resolution tokens per frame: 70 Supported MIME types: video/x-flv, video/quicktime, video/mpeg, video/mpegs, video/mpg, video/mp4, video/webm, video/wmv, video/3gpp
	Audio	Maximum audio length per prompt: Approximately 8.4 hours, or up to 1 million tokens Maximum number of audio files per prompt: 1,000 Maximum inline part size (GenerateContent API): 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB Speech understanding for: Audio summarization, transcription, and translation 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
	Parameter defaults	Temperature: 1.0 (fixed; custom values ignored) topP: 0.95 (fixed; custom values ignored) topK: 64 (fixed; custom values ignored) candidateCount: 1 (fixed)
Supported regions	Model availability	Global: global Multi-region: us, eu
	ML processing	Multi-region: us, eu
	Provisioned Throughput	Global: global Multi-region: us, eu
	Standard PayGo	Global: global Multi-region: us, eu
	Priority PayGo	Global: global Multi-region: us, eu
Knowledge cutoff date	March 2026
Versions	gemini-4-hydrogen Launch stage: GA Release date: November 12, 2026
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	Batch inference	Data residency CMEK VPC-SC AXT
	Context caching	Data residency CMEK VPC-SC AXT
	See Security controls for more information.