G
GOOGLE / gemini-4-neon

Gemini 4 Neon

Google multimodal model generally available since November 18. It combines coding, scientific reasoning and document work. It accepts text, images, audio, video and PDF and produces text, with a shared context window of approximately one million tokens.

01 / SUMMARY

The essential

ORIENTATIONCoding, science and document work

Primary use stated or inferred cautiously from official documentation.

CONTEXT1,048,576 tokens shared by input and output

Maximum input capacity when published by the source.

EXIT65,536 synchronous tokens, up to 1,048,576 with long decode

Documented maximum generation limit.

ACCESSGemini API · general availability

Verified availability channels.

MODEL TYPEText and reasoning · Code · Multimodal

Primary functional family and verified specialties.

LICENSEProprietary

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDgemini-4-neon
Model typeText and reasoning · Code · Multimodal
Access modelPaid proprietary
LicenseProprietary
DeploymentHosted API
Release18 NOV 2026
Knowledge cutoffNot published
EntranceText · Image · Video · Audio · PDF
ExitText
Context window1,048,576 tokens shared by input and output
maximum output65,536 synchronous tokens, up to 1,048,576 with long decode
Reasoninglow, medium, high and xhigh; high by default
Published toolsFeatures · Web search · Computer use
Structured OutingsStructured Outings
Batch processingAvailable
Prompt cacheImplicit caching only; no explicit caching
Fine-tuningNot published
Verified platformsGemini API · Google AI Studio
BEST SUITED FOR

Analyze long documents, reason about charts and carry out coding tasks with tools. Supports generateContent and the Interactions API. Office and OpenDocument processing allows selection of pages, sheets, cells or multimedia intervals.

WORTH MONITORING

The synchronous maximum is 65,536 tokens. Long output requires long decode and shares the window with input. Native image and audio generation are unsupported. Remove cached_content when migrating: only implicit caching is supported. Access and quotas depend on plan and region.

03 / CAPABILITIES

What it can do

01

Orientation

Analyze long documents, reason about charts and carry out coding tasks with tools. Supports generateContent and the Interactions API. Office and OpenDocument processing allows selection of pages, sheets, cells or multimedia intervals.

02

Context

1,048,576 tokens shared by input and output · 65,536 synchronous tokens, up to 1,048,576 with long decode

03

Tools and integration

Features · Web search · Computer use

04

Access

Gemini API · general availability

Input modalities
TextImageVideoAudioPDF
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputUSD 3 / 1M tokensStandard API rate
Cached inputUSD 0.15 / 1M tokensReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputUSD 15 / 1M tokensMay include reasoning tokens
Batch inputUSD 1.50 / 1M tokensAsynchronous processing
Batch outputUSD 7.50 / 1M tokensAsynchronous processing

Standard costs USD 3 input and USD 15 output per million tokens, including reasoning. Implicit cache reads cost USD 0.15 and require eligible prefixes from 4,096 tokens. Batch and Flex cost USD 1.50 and USD 7.50; Priority costs USD 5.40 and USD 27. Tools and searches may add charges. Neon has no free tier.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

The card reports 65.2% on Terminal-bench 4.1 with cheating adjustment and 95.2% F1 on GraphWalks BFS from 256K to 1M tokens. These are Google results in its evaluation environments, not tests reproduced by Inferama. Context, effort or tool changes may affect results.

BenchmarkResultMetricSource
Terminal-bench 4.165.2%Cheating-adjusted accuracyView source ↗
GraphWalks BFS 256K–1M95.2%F1 · BFS from 256K to 1M tokensView source ↗

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

gemini-4-neon

General availability; Batch, Flex and Priority are service modes, not new models.

07 / SOURCES

Traceability