Skip to content
AI Atlas
ModelPreviewClosed / proprietary

Gemini 3 Flash Preview

Googlefamily · Gemini 3ai.google.dev/gemini-api/docs/models/gemini-3-fl

Frontier-class performance rivaling larger models at a fraction of the cost.

Open in Graph
data quality71

Updated 4 h ago · first seen 11 Sept 2026

model_01M293V7V4D72KG1WYXTBT3Z8W

Overview

Identity

Canonical model
Yesidentity confidence: highOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
None recorded — closed weightsofficial_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
1
API aliases
gemini-3-flash-previewgemini-3-flash-reasoninggoogle/gemini-3-flash-previewIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Closed / proprietary— weights not available; 7 dimensions unknown.

Weights are not available; the model is reachable only through an API or a product.

  • Weights

    No

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Status

Source:Google AI for Developers (Gemini API docs)T1observed 14 h agohigh

API model id

Source:Google AI for Developers (Gemini API docs)T1observed 14 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Capabilities

Modalities

Modalities
audiodocumentimagetextvideo
Input
audiodocumentimagetextvideo
Output
text

Capabilities

  • Tool calling

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Structured output

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Reasoning

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Vision

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Audio

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Fine-tuning available

    Unavailable

Context window

Source:Google AI for Developers (Gemini API docs)T1observed 14 h agohigh

Max output

Source:Google AI for Developers (Gemini API docs)T1observed 14 h agohigh

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Benchmarks7

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthard1−27.3 ptvs gpt-5.6-solobs. 11 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−18.7 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentversion4.31−27.0vs Claude Fable 5.1obs. 11 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−5.37 ptvs Grok 4.3obs. 11 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−22.6 ptvs Claude Fable 5.1obs. 11 Sept 2026artificialanalysis.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−6.94 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−6.46 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 7 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing3

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inCache writeOutput / 1MBatch in / outPer image / requestNative unitsStatusObservedSource
Google Gemini APIcheapest outputgoogle/gemini-3-flash-preview:batch1.05Mout 65.5K———$0 / ——active4 h agosince 11 Sept 2026openrouter.aiT2
Google Gemini APIgemini-3-flash-preview—$0.05—$0.25 / $1.5—flex_input_per_mtok=0.25audio_input_per_mtok=1flex_output_per_mtok=1.5+4active4 h agosince 11 Sept 2026ai.google.devT1
Google Gemini APIgoogle/gemini-3-flash-preview1.05Mout 65.5K$0.05$0.083—$0 / ——active4 h agosince 11 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of Gemini 3 Flash Preview$0$1$2$3$4Sept 26Sept 26Sept 26Google Gemini API: first observed → $3 · 11 Sept 2026Google Gemini API: $3 → $1.5 · 11 Sept 2026
  • Google Gemini API
  • Google Gemini API$3 → $1.511 Sept 2026
  • Google Gemini APIfirst observed $311 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Gemini 3 Flash Preview$0$0.20$0.40$0.60Sept 26Sept 26Sept 26Google Gemini API: first observed → $0.50 · 11 Sept 2026Google Gemini API: $0.50 → $0.25 · 11 Sept 2026
  • Google Gemini API
  • Google Gemini API$0.50 → $0.2511 Sept 2026
  • Google Gemini APIfirst observed $0.5011 Sept 2026

Versions & Artifacts0

Version history

Context windowfirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Statusfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline2

Full timeline →
  • Capabilities changedModelGemini 3 Flash PreviewGoogle

    Gemini 3 Flash Preview: capabilities changed from ["Caching", "Code execution", "Computer use", "File searc… to ["caching", "code_execution", "computer_use", "file_searc…

    CapabilitiesCaching, Code execution, Computer use, File search, Function calling, Grounding with Google Maps, Search grounding, Structured outputs, Thinking, URL context→caching, code_execution, computer_use, file_search, function_calling, maps_grounding, reasoning, search_grounding, structured_output, url_contextgoogle
    ai.google.dev
  • Property changedModelGemini 3 Flash PreviewGoogle

    Gemini 3 Flash Preview: family changed from Gemini to Gemini 3

    FamilyGemini→Gemini 3google
    ai.google.dev

Change history27

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Mar 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Gemini 3 Flash Preview was not yet in AI Atlas on 12 Mar 2026

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
27 claims · 23 properties4 conflicting

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
Gemini → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
17 Dec 2025 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Statusstatus1

Claim history for Status
ValueValid from → toStatusSourceConfidenceExtractor
preview → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
1.05M tokens → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
65.5K tokens → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Modalitiesmodalities3conflicting claims

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, image, text, video → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text, video → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, pdf, text, video → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Input modalitiesmodalities_input3conflicting claims

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, image, text, video → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text, video → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
text, image, video, audio, pdf → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
Gemini → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
gemini-3-flash-preview → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Audioaudio1

Claim history for Audio
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Capabilitiescapabilities1

Claim history for Capabilities
ValueValid from → toStatusSourceConfidenceExtractor
Caching, Code execution, Computer use, File search, Function calling, Grounding with Google Maps, Search grounding, Structured outputs, Thinking, URL context → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Frontier-class performance rivaling larger models at a fraction of the cost. → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

File inputfile_input1

Claim history for File input
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Latest updatelatest_update1

Claim history for Latest update
ValueValid from → toStatusSourceConfidenceExtractor
2025-12 → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
google/gemini-3-flash-preview → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Versionsversions1

Claim history for Versions
ValueValid from → toStatusSourceConfidenceExtractor
{"preview":["gemini-3-flash-preview"]} → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

28

Source tiers

T1T219 / 9

Freshest observation

4 h ago

Conflicts

16 flagged

Source documents 5

Source documents
SourceDocumentTypeTierLast observedSnapshots
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview model_pageT1· Official4 h ago17
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/models model_docsT1· Official4 h ago18
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/pricing pricingT1· Official4 h ago18
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary4 h ago7
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary12 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (71/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →