
Gemini 4 Neon Launch Guide for Access, Features, and Migration
Google released Gemini 4 Neon on November 18. See where to try it, what benchmarks and context limits mean for your work, and how to migrate an app.
On this page
If you evaluate models through EvoLink, pick a task your team already runs and an outcome you can check. A release-note summary gives you a sense of the model’s writing style. A reproducible production bug or a report with known totals tells you whether to move real traffic.
Gemini 4 Neon specifications at a glance
| What to check | Gemini 4 Neon |
|---|---|
| Google model ID | gemini-4-neon |
| Developer access | Paid Gemini API and Google Cloud's Gemini Enterprise Agent Platform |
| App and coding-tool access | Eligible Google AI Pro and Ultra users in Gemini and Antigravity |
| Gemini API context | 1,048,576 tokens shared by input, thinking, and output |
| Gemini API output | 65,536 tokens for thinking and output combined by default in a synchronous response. Long decode can extend output within the shared context budget |
| Inputs and output | Text, images, audio, video, and PDF input. Text output |
| Thinking levels | low, medium, high (default), and xhigh |
Where Gemini 4 Neon is available
gemini-4-neon, can come with different context limits, built-in tools, and billing rules. Pick the access route that matches the workflow you want to test.| Surface | What you can try | What to verify |
|---|---|---|
| Google AI Studio and Developer API | Try the model in AI Studio. The paid Developer API exposes Neon through Interactions and GenerateContent | Confirm project billing and test the exact API method your application uses |
| Google Cloud | Google documents the global endpoint and the us and eu multi-regions | Match the project's location and deployment requirements |
| Gemini app and Antigravity | Eligible Pro and Ultra users can try Neon. Antigravity documents up to 512K context | Check your plan and measure quota in that product separately from API spend |
| Cursor and third-party gateways | Cursor lists 200K context with a 1M maximum. OpenRouter and Vercel list google/gemini-4-neon | Check tool support, enabled context, and billing through that specific route |
Which tasks to try first with Neon
| If your team needs to… | Start the evaluation here | What a good result looks like |
|---|---|---|
| Run routine edits or extract known fields at volume | Hydrogen | Valid output with few retries |
| Fix a recurring bug that crosses modules | Neon high | The failing case passes, existing behavior holds, and the patch stays in scope |
| Reconcile a report across tables, charts, and PDFs | Neon high | Important figures trace back to their source, and missing evidence is flagged |
| Resolve an ambiguous architecture or debugging problem | Carbon as a baseline | The team can reproduce the diagnosis and validate the proposed change |
Suppose the PDF summary of a monthly report disagrees with the spreadsheet. Give Neon the source files, reporting period, and fields to reconcile. Ask for a worksheet name, cell range, or page reference for every discrepancy. Include a known mismatch and a figure with no traceable source. A passing result finds the mismatch and flags the unsupported figure.
What the launch demos and third-party tests show
xhigh in AutomationBench. Each case checked the final state of simulated apps. A support workflow can apply that idea by verifying the ticket's final owner and status, checking that no duplicate ticket was created, and requiring the agent to surface an unresolved account match. A plausible completion message alone leaves these failures invisible. Zapier AutomationBench report
When to use Orchestrator in Antigravity
Orchestrator (Neon), Neon plans and reviews while Hydrogen implements and runs checks. If an unexpected interface or a failed check invalidates the plan, control returns to Neon. This is a useful option to test when discovery is difficult and most edits are straightforward, such as a package migration with a few compatibility decisions. Try direct Neon as the baseline when the difficult reasoning continues throughout implementation. The Orchestrator setting has a fixed configuration, while direct model selection exposes the thinking level. Antigravity model selectionHow much to budget for the first test
How to migrate an existing Gemini app to Neon
medium, while Neon defaults to high, so leaving both at their defaults also changes the amount of reasoning the models are allowed to use. Google migration checklistCheck three areas when upgrading from Gemini 3.
- Caching. Replace explicit cache creation and references such as
cached_contentwith a flow that works with Neon's implicit caching. - Multi-turn state and thought signatures. If the client manages GenerateContent history, return the signatures Google sent without changing them. Follow the Interactions API's state contract when using that interface.
- Tools and structured output. Conform to the API schema for function tools and structured output. Validate the follow-up turn after a tool returns its result. Google migration checklist
Make long generation resumable
Pick a service tier for your deadline
FAQ
When did Gemini 4 Neon launch?
Google announced it on November 18, 2026.
Is it free through the Gemini API?
Google lists Neon on the paid API tier. App and IDE access follow separate subscription rules.
What is the Google API model ID?
gemini-4-neon.Can I send a video or PDF?
Google lists both as supported inputs. Neon returns text.
Can it output a million tokens in one request?
Thinking and output share the default synchronous limit of 65,536 tokens. Use long decode for longer generation and keep the total within the shared context budget.
Which thinking level should I try first?
high for a complex task. Try medium when the task has clear checks, or test xhigh on cases that stall at high.Should I replace Hydrogen or Carbon?
Evaluate Neon on a task class you can verify. Keep Hydrogen or Carbon wherever it already meets your quality, time, and cost requirements.


