

Explore Gemini 4 Neon
Google introduced Gemini 4 Neon on November 18, 2026 for complex coding, knowledge work, and scientific workflows. Its Gemini API model ID is gemini-4-neon. Check your Tabbit account’s model picker for availability.
Use in Tabbit Gemini 4 Neon
Featured showcases & prompts
Gemini 4 Neon model ID and Gemini API specifications
The stable model ID in the Gemini API is gemini-4-neon. It accepts text, images, video, audio, and PDFs, and returns text. Input and output share a budget of 1,048,576 tokens, and the default output limit for synchronous calls is 65,536 tokens.
Estimating Gemini 4 Neon API costs by inference mode
Apply the corresponding rate to uncached input tokens, input tokens served from the implicit cache, and output tokens including thinking tokens. For the same token usage, Batch and Flex each cost half as much as Standard, while Priority costs 1.8 times as much.
Calling Gemini 4 Neon through OpenRouter and choosing an upstream endpoint
Send requests to OpenRouter with google/gemini-4-neon. OpenRouter picks the upstream endpoint by default. To pin requests to Google AI Studio, use provider.only to limit eligible endpoints and allowfallbacks: false to disable failover. The endpoint determines .
Regions and inference settings for Gemini 4 Neon on Google Cloud
To use the generally available gemini-4-neon model on Google Cloud, confirm enterprise customer eligibility and choose global, us, or eu. For workloads with machine learning processing location requirements, the documentation lists only the us and eu multi-reg.
Choosing Gemini 4 Neon or Orchestrator in Google Antigravity
Choose Gemini 4 Neon to set the thinking level yourself, or choose Orchestrator (Neon) to have Neon plan the work and Hydrogen edit code and run tests in the same session.
Selecting Gemini 4 Neon in Cursor Agent and checking charges
Select Gemini 4 Neon directly in the model picker in Cursor Chat or Agent. Cursor lists it as a third-party model and deducts usage charges from the prepaid balance on individual plans under The X Subscription or from the Other Models usage pool on eligible le.
Reviews and field notes
Science, coding, and multimodal benchmarks in the Gemini 4 Neon model card
Google DeepMind reports that Neon scored 84.0% on RiemannBench and 39.0% and 12.8% on SWE-sweep in two different agent environments, so consider both the reasoning tier and the agent environment when choosing a model.
Gemini 4 Neon benchmark scores, latency, and cost across four reasoning tiers
In Artificial Analysis's evaluation, moving Gemini 4 Neon from High to Xhigh raised its overall index score from 60 to 61, added 6.7 minutes per index task, and increased the weighted cost per task by $2.70.
Gemini 4 Neon (High) ranks second on Agent Arena's real-world task leaderboard
In Arena's published snapshot, Gemini 4 Neon (High) ranked second with 1,336 points based on about 4,200 agent sessions from real users. Its median cost per task was $2.82, 53% lower than third-place Claude Opus 5.5 (Max), which trailed Neon by one point. Aren.
Gemini 4 Neon pass rates and costs across four reasoning tiers on Zapier AutomationBench
Across Zapier's 657 tasks, XHigh passed 13 more in total than High, raising the pass rate from 54.3% to 56.3% and the estimated cost per attempt from $0.88 to $1.69. Results by effort.
Gemini 4 Neon scores, costs, and runtimes on Vals Index 2.2
In the November 18, 2026 snapshot of Vals Index 2.2, Gemini 4 Neon at XHigh scored 70.87% and ranked second out of 42 models, averaging $7.40 and 31 minutes 25 seconds per test. It scored 0.44 percentage points below first-place Claude Fable 5.2 and cost about.
Explore Gemini 4 Neon
Explore Gemini 4 Neon prompts, API settings, and evaluations. Compare reasoning levels, task costs, and test conditions with links to original sources.