Citation and evidence

Gemini 4 Neon

Report a problem with this article

Edit article
More

Cite this article

Gemini 4 Neon is a multimodal reasoning model from Google DeepMind, announced on November 18, 2026 for software engineering, analytical work, and scientific tasks.[1] Google adapted it from Gemini 4 Carbon.[2] The stable API identifier is gemini-4-neon; the model accepts text, images, audio, video, and PDFs and produces text.[3]

Google positions Neon between Carbon for demanding extended work and Hydrogen for everyday execution. These are workload distinctions rather than a guarantee that one model wins every comparison.[4] Neon also serves as a planner in Google Antigravity, where an Orchestrator workflow can delegate implementation to Hydrogen.[5]

Specifications and access

PropertyPublished specification
Stable Developer API model IDgemini-4-neon[3]
Unified input and output window1,048,576 tokens[3]
Default synchronous output limit65,536 tokens[3]
Extended outputUp to the unified window using long decode, with input consuming part of that budget[6]
API thinking levelslow, medium, high (default), xhigh[4]
Knowledge cutoffMarch 2026[2]
Cloud launch stageGenerally available, released November 18, 2026[7]

Expanded article table

The unified window includes the prompt, reasoning, tool calls, and final answer. A request containing a long input therefore has less room left for generation. The output allowance is not an additional million tokens on top of a million-token input.[6][10]

Availability depends on the product:

ChannelPublished access conditions
Gemini Developer APIPaid tier, through generateContent or the Interactions API[4]
Google AI StudioGoogle AI Pro and Ultra plans, alongside API access[4]
Gemini appGoogle AI Pro and Ultra subscribers, through the model selector[1]
AntigravityPaid Google AI Pro and Ultra subscribers across the app, CLI, and IDE extensions; enterprise access through Gemini for business[5]
Gemini Enterprise Agent PlatformVerified enterprise customers in selected regions; global, us, and eu endpoints[7]

Expanded article table

Antigravity's announced context limit is up to 512K tokens, separate from the API's 1,048,576-token window.[8] Product entitlements and context settings should not be inferred from the underlying model's maximum.

Reasoning and long responses

The API's thinking_level controls the amount of reasoning. Google's Neon guide recommends high for complex tasks and xhigh when additional reasoning is worth greater latency and token consumption. low and medium reduce those costs for more responsive interactions.[4] These API defaults do not specify the default selected by every application.

Thinking uses the same generation allowance as the answer. Google's thinking documentation describes thought steps in the Interactions API, including an encrypted signature and an optional summary. The summary is a representation exposed by the API, rather than unrestricted access to the model's internal reasoning. generateContent represents signatures as metadata on response parts instead.[9]

Long decode splits a response into continuation segments. Neon permits up to 65,536 tokens per segment for streaming and non-streaming calls. With the Interactions API, setting background=true and a larger max_output_tokens lets Google's servers run the continuation loop; a client can instead manage continuation itself. Merely enabling background mode without increasing the limit still stops at 65,536 tokens.[6]

A minimal Interactions request can set the reasoning level explicitly:[4]

from google import genai

client = genai.Client()
interaction = client.interactions.create(
    model="gemini-4-neon",
    input="Review this service design for race conditions.",
    generation_config={"thinking_level": "high"},
)
print(interaction.output_text)

This example uses the Google Gen AI SDK and its configured authentication. It makes a text request; access to a repository, terminal, or external service requires the surrounding application to provide those tools.

Tools, files, and migration

The Developer API lists function calling, structured outputs, code execution, computer use, file search, URL context, and grounding with Google Search and Maps as supported. Agentic video understanding is supported but defaults to static processing. Tool retrieval is a preview capability. Neon does not provide image generation, audio generation, or the Live API.[3]

On Gemini Enterprise Agent Platform, Neon additionally accepts Office and OpenDocument formats, including Word, PowerPoint, Excel, ODT, ODP, and ODS files, inline or from Cloud Storage. The Cloud specification also lists system instructions and RAG Engine support, but not tuning.[7] These Cloud capabilities should not be assumed to have identical upload paths or limits in every consumer interface.

Migration from older models requires more than changing the model name. Google's Cloud developer guide identifies these API differences:[10]

Integration concernNeon behavior
Thinking configurationUse LOW, MEDIUM, HIGH, or XHIGH on GenerateContent; thinking_budget and MINIMAL cause HTTP 400 errors
SamplingCustom temperature, top_p, and top_k values are ignored
Parallel tool callsPreserve thought signatures; only the first functionCall part in a parallel turn carries the signature
Conversation historyPreserve previous model turns and signatures rather than reconstructing their contents
Explicit cache objectsUnsupported; use implicit caching
Cloud locationUse global, us, or eu

Expanded article table

The guide also warns that continuation behavior depends on the API endpoint and SDK version. Its Cloud long-decode implementation uses v1beta1; changing the model, system instruction, or function declarations between continuation segments causes validation errors.[10]

API prices and caching

The following Gemini Developer API prices were checked on November 22, 2026. Amounts are US dollars per million tokens; output prices include thinking tokens.[11]

Inference modeUncached inputCached inputOutput
Standard$3.00$0.15$15.00
Batch$1.50$0.075$7.50
Flex$1.50$0.075$7.50
Priority$5.40$0.27$27.00

Expanded article table

There is no free API tier for Neon. Google's Neon guide specifies flat token pricing across the unified window.[4] The published output rate covers reasoning as well as visible answers; grounding can add separately billed search queries.[11]

Context caching is implicit and enabled by default, with a 4,096-token minimum for Neon. Repeated prompt prefixes can improve the chance of a hit, but meeting the threshold does not guarantee one. Google's caching documentation says Gemini 4 reprocesses the previous request's last 2,050 tokens at the standard input rate when the next turn adds fewer than 2,050 tokens. The response's usage.total_cached_tokens reports actual cached tokens.[12]

Token-price comparisons also need dates. Carbon's published Standard prices are temporarily $2 input and $10 output through November 30, 2026, rising to $4 and $20 on December 1. Consequently, Neon's $3/$15 is above Carbon's promotional rates and below its scheduled standard rates.[11]

Evaluation results

Google published the following November 2026 results. They measure particular benchmarks and agent setups, rather than a single general measure of intelligence.[13]

BenchmarkNeon result
CursorBench 4.165.4%
Terminal-Bench 4.1, cheating-adjusted accuracy65.2%
FrontierCode 2.046.2%
SWE-sweep, Antigravity provider harness39.0%
SWE-sweep, mini-SWE harness12.8%
Agents' Last Exam v1.175.8%
RiemannBench84.0%
Terminal-Bench-Science 0.170.5%
Chartography73.5%
GraphWalks, 256K-1M BFS F195.2%
CWE-bench v270.7%
SEC-bench Pro90.5%

Expanded article table

Google's methodology generally uses the highest thinking setting, except where stated, and reports pass@1 unless specified otherwise. FrontierCode uses high. The two SWE-sweep numbers use different harnesses; the Antigravity setup includes subagents, so the difference cannot be attributed solely to the model. Cybersecurity evaluations are an exception to the report's usual safety-filter setting.[13]

Independent evaluators provide further context. Artificial Analysis's November 18 analysis recorded an Intelligence Index score of 61 at xhigh. Its measured cost was $6.44 per task versus Carbon's $7.76 using non-discounted pricing, with approximately 21 versus 36 minutes per task. Those are measurements of that evaluation workload, not general API latency guarantees. Artificial Analysis also found that higher effort did not win every subtest: GDP.pdf scored 33.4% at high and 28.0% at xhigh.[14]

Zapier's AutomationBench leaderboard, version 1.0.6, listed Neon at 56.32% and $1.69 per task on xhigh, 54.34% and $0.88 on high, and 53.27% and $0.58 on medium. The benchmark grades final state changes in simulated business systems using deterministic assertions, rather than judging only an agent's written answer.[15]

Benchmark scores require their own interpretation. Cognition defines FrontierCode 2.0's score as a weighted rubric aggregate, assigning zero to solutions that fail blocking criteria.[16] Riemann-Bench's research paper describes privately held, expert-written mathematics problems with verifiable closed-form answers and agents permitted coding and search tools.[17] Neither score represents the fraction of arbitrary real-world jobs that Neon can complete.

Safety and limitations

The model card acknowledges hallucinations. Its March 2026 knowledge cutoff also means newer information requires external context or retrieval.[2] Google's announcement reports improvements in internal fabrication and agent-behavior tests, including a 99.2% pass rate on its agent honesty evaluation. Those are attributed evaluation results, not a guarantee of truthful answers or error-free tool use.[1]

For frontier risks, Google performed a Material Capability Change assessment against Gemini 4 Argon. It reported that Neon remained below the threshold requiring another full suite of critical-capability evaluations and carried forward Argon's threshold determinations. These included biological and cybersecurity critical-capability thresholds that could not be ruled out. The model card linked a forthcoming dedicated Safety & Security Report when checked on November 22, 2026.[2]

The separate cyber access described at launch was to roll out to trusted defenders through Google's Fairwind Program.[1] General availability of the standard model does not imply unrestricted availability of every cyber configuration or removal of usage policies.

Continue reading

More to read

Topics:AI ModelsGoogle DeepMindLarge Language ModelsMultimodal AIReasoning Models

References

  1. ^1 ^2 ^3 ^4Google, Koray Kavukcuoglu. Introducing Gemini 4 Neon. November 18, 2026.
  2. ^1 ^2 ^3 ^4Google DeepMind. Gemini 4 Neon model card. November 18, 2026; accessed November 22, 2026.
  3. ^1 ^2 ^3 ^4 ^5Google. Gemini 4 Neon, Gemini Developer API model specifications. Accessed November 22, 2026.
  4. ^1 ^2 ^3 ^4 ^5 ^6 ^7Google. What's new in Gemini 4 Neon. Accessed November 22, 2026.
  5. ^1 ^2Google Antigravity Team. Gemini 4 Neon in Google Antigravity. November 18, 2026.
  6. ^1 ^2 ^3Google. Long decode, Gemini Developer API. Accessed November 22, 2026.
  7. ^1 ^2 ^3Google Cloud. Gemini 4 Neon, Gemini Enterprise Agent Platform specifications. Accessed November 22, 2026.
  8. ^Google AI Developers Forum, rody. Gemini 4 Neon and Orchestrator (Neon) are now available in Google Antigravity. November 18, 2026.
  9. ^Google. Gemini thinking. Accessed November 22, 2026.
  10. ^1 ^2 ^3Google Cloud. Developer's guide to Gemini 4 Neon. Accessed November 22, 2026.
  11. ^1 ^2 ^3Google. Gemini Developer API pricing. Accessed November 22, 2026.
  12. ^Google. Context caching. Accessed November 22, 2026.
  13. ^1 ^2Google DeepMind. Gemini 4 Neon model evaluation: Approach, methodology and results. November 2026; accessed November 22, 2026.
  14. ^Artificial Analysis. Google continues to accelerate its release cadence with Gemini 4 Neon. November 18, 2026.
  15. ^Zapier. AutomationBench leaderboard. Version 1.0.6; accessed November 22, 2026.
  16. ^Cognition. FrontierCode 2.0. October 27, 2026.
  17. ^Suhaas Garre, Erik Knutsen, Sushant Mehta, and Edwin Chen. Riemann-Bench: A Benchmark for Moonshot Mathematics. arXiv:2604.06802, version 3, June 23, 2026.

Improve this article

Add missing citations, update stale details, or write a clearer explanation. Anyone can edit: changes go live when you publish, and every edit is checked by an editor.

1 revision · v1 · 1,829 words · full history

Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify

Research and drafting on this wiki are AI-assisted, under named human editorial standards. How AI is used here

Cite this page: AI Wiki. "Gemini 4 Neon." aiwiki.ai, updated 22 Nov 2026. CC BY 4.0. https://aiwiki.ai/wiki/gemini_4_neon

Edit article