Skip to content
Back to feed

November 18, 2026 · Google CloudFeature

Gemini 4 Neon generally available, with a 1,048,576-token input and output limit

Gemini 4 Neon (GA)

Gemini 4 Neon (gemini-4-neon) is generally available (GA) in Gemini Enterprise Agent Platform. Gemini 4 Neon is a Google Frontier Model subject to Section 34 of the Service Specific Terms (for details, see Abuse monitoring) and delivers high-performance coding, multi-step reasoning, and multimodal understanding at low latency for agentic enterprise workflows:

  • Unified 1,048,576-token limit and long decodes: Supports a unified 1,048,576-token input and output limit, where output includes thinking, function calls, and the final response. Single foreground segments generate up to 65,536 output tokens for streaming and non-streaming requests. Long decodes (continuation_token) extend output up to 1,048,576 tokens (minus input tokens) on the Interactions API and GenerateContent (v1beta1). The Interactions API also supports asynchronous server-managed background execution (background=true).

  • Thinking levels (LOW, MEDIUM, HIGH, and XHIGH): Supports four thinking levels, with HIGH as the default and XHIGH for deep reasoning workloads. Setting thinking_budget or thinking_level="MINIMAL" returns an HTTP 400 validation error.

  • Implicit context caching with durable caching: Supports automatic implicit context caching with durable caching enabled by default for shared prompt prefixes of 4,096 tokens or more (explicit context caching isn't supported).

  • Cache write control and pricing: 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 Gemini 4 pricing.

  • Office and OpenDocument file inputs: Supports Microsoft Office (.docx, .dotx, .doc, .pptx, .ppt, .xlsx, .xls) and OpenDocument (.odt, .odp, .ods) files inline or from Cloud Storage (gs://), including inside multimodal FunctionResponse parts.

  • Capabilities, consumption options, and endpoints: Available on the global endpoint and in the us and eu multi-regions across GenerateContent, the Interactions API, and the OpenAI compatibility Chat Completions API. Supports function calling, code execution, computer use, URL context, and Agentic video understanding. Grounding options include Grounding with Google Search, Google Maps, Web Grounding for Enterprise, and Parallel and Exa Web Search. Consumption options include Standard PayGo with Usage Tiers, Priority PayGo, Off-peak PayGo, batch inference, and Provisioned Throughput.

For model specifications, code examples, and migration guidance from Gemini 3 models, see Gemini 4 Neon, the developer's guide to Gemini 4 Neon, and Get started with Gemini 4.

Text from the Google Cloud release notes, licensed under CC BY 4.0. Source: Google Cloud release notes.

Free. Unsubscribe any time.

All Gemini Enterprise Agent Platform changes