Google
·Released on Dec 17, 2025

Gemini 3 Flash API Benchmarks, Pricing & Provider Data

Compare Gemini 3 Flash with another model

Choose a model to open its comparison page.

Share on X
LLM

Gemini 3 Flash benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0014/M. Gemini 3 Flash free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.

Google Gemini 3 Flash is a next-generation fast multimodal model for responsive assistants, document understanding, and high-throughput API traffic.

Quality
#38of 112
65.0
LMSpeed score
Speed
162char/s
7.48 s
Cost
#85of 186
$0.0014/ 1M · 8:1 in:out
$0.0002 in · $0.0012 out

Category Performance

Observed-capability estimates with uncertainty reported separately from independent benchmark families.

Coverage
8 / 8
Methodology
V3.0
Category PerformanceObserved-capability estimates with uncertainty reported separately from independent benchmark families.Agents43.1Coding52.7Reasoning52Knowledge53.7Math51.5Multilingual58.5Multimodal50.9Instruction following47.9
#1Multilingual58.5Provisional1/4 Measured dimensions
80% interval: 41.575.5
cross language understanding58.5
global_mmlu · aa_global_mmlu_lite
multilingual generationPrior only
reasoning transferPrior only
low resource robustnessPrior only
#2Knowledge53.7Provisional1/4 Measured dimensions
80% interval: 39.767.7
broad knowledge53.7
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#3Coding52.7Estimated2/4 Measured dimensions
80% interval: 41.563.9
code generation57.3
livecodebench · livecodebench / scicode · aa_sci_code
repository engineering48.2
vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#4Reasoning52RatedGlobal rank #353/4 Measured dimensions
80% interval: 43.460.7
abstract logicPrior only
scientific causal51
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraints59.9
mmlu_pro · mmlu_pro
evidence verification45.1
lcr · lcr
#5Math51.5Provisional1/4 Measured dimensions
80% interval: 35.467.6
foundational mathPrior only
competition mathPrior only
proof frontier51.5
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#6Multimodal50.9Provisional1/4 Measured dimensions
80% interval: 34.567.2
perception ocrPrior only
document spatialPrior only
visual reasoning50.9
benchlm_category_multimodal · benchlm_category_multimodal_grounded
video actionPrior only
#7Instruction following47.9Provisional1/4 Measured dimensions
80% interval: 31.963.9
constraint followingPrior only
structured outputPrior only
novel instruction generalization47.9
ifbench · aa_if_bench
long multiturn instructionPrior only
#8Agents43.1RatedGlobal rank #553/4 Measured dimensions
80% interval: 34.252.0
planning53.9
deep_planning · gert_labs
tool use42
tau · tau2_bench
environment executionPrior only
recovery reliability33.4
claw_eval · claw_eval / jobbench · job_bench

Specifications

Input and output token limits for this model, plus how it ranks on long-context understanding.

INPUT
1.0Mtokens
1.3K pages of text
OUTPUT
65.5Ktokens
8K128K1M4M
1.0M

Features

Technical Details

Input
Output
Released
Dec 2025
Documentation
Tokenizer
Gemini
Architecture
text+image+file+audio+video->text
Moderated
No
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Rankings

Excels at

It's decent at

Falls behind in

Detailed scores

Updated: Sep 13, 2026

Overall

undefined metric} other undefined metrics}}

Overall score65.0#38 / 112
Overall score
LMSpeed rank#38
Score65.0
UpdatedSep 10, 2026
Confidence3

Pricing

undefined metric} other undefined metrics}}

Input price$0.500/M#85 / 186Output price$3.00/M#99 / 186
Input price
LMSpeed rank#85
Score$0.500/M
UpdatedSep 13, 2026
Confidence4
Output price
LMSpeed rank#99
Score$3.00/M
UpdatedSep 13, 2026
Confidence4

Agents

V3.0

undefined metric} other undefined metrics}} · Rated

Score43.1#5580% interval34.2–52.03/4 Measured dimensionsClaw-Eval49.2#24 / 27Τ²-bench results43.3#69 / 82
Dimensions and evidence
Planning & decomposition53.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.53 · q 1.00
Tool use42
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z -1.16 · q 1.00
Environment & long-horizon executionPrior only
Recovery & completion reliability33.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
claw_eval · claw_eval · z -1.65 · q 1.00
jobbench · job_bench · z -1.54 · q 1.00
Claw-EvalV3 evidence
LMSpeed rank#24
Score49.2
UpdatedSep 10, 2026
Confidence3
Τ²-bench resultsV3 evidence
LMSpeed rank#69
Score43.3
UpdatedSep 10, 2026
Confidence3
Gert LabsV3 evidence
LMSpeed rank#16
Score56.6
UpdatedSep 10, 2026
Confidence3
JobBenchV3 evidence
LMSpeed rank#21
Score11.4
UpdatedSep 10, 2026
Confidence3
Terminal-Bench 2.1 (Vals)
LMSpeed rank#31
Score53.9
UpdatedSep 10, 2026
Confidence3

Coding

V3.0

undefined metric} other undefined metrics}} · Estimated

Score52.780% interval41.5–63.92/4 Measured dimensionsLiveCodeBench79.7%#19 / 115Vibe Code Bench20.2#21 / 33
Dimensions and evidence
Code generation57.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 0.94 · q 1.00
scicode · aa_sci_code · z 0.65 · q 1.00
Repository engineering48.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
vibecode · vibe_code_bench · z -0.22 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
LiveCodeBenchV3 evidence
LMSpeed rank#19
Score79.7%
UpdatedSep 13, 2026
Confidence4
Vibe Code BenchV3 evidence
LMSpeed rank#21
Score20.2
UpdatedSep 10, 2026
Confidence3
Coding score
LMSpeed rank#16
Score66.7
UpdatedSep 10, 2026
Confidence3
LiveCodeBench (Vals)
LMSpeed rank#21
Score85.6
UpdatedSep 10, 2026
Confidence3
SWE-bench (Vals)
LMSpeed rank#29
Score75.0
UpdatedSep 10, 2026
Confidence3
AA-SciCodeV3 evidence
LMSpeed rank#36
Score49.9
UpdatedAug 20, 2026
Confidence1
EEBench
LMSpeed rank#15
Score19.5
UpdatedAug 20, 2026
Confidence1

Reasoning

V3.0

undefined metric} other undefined metrics}} · Rated

Score52#3580% interval43.4–60.73/4 Measured dimensionsMMLU-Pro88.2%#7 / 129GPQA81.2%#95 / 218
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning51
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z -0.31 · q 1.00
gpqa · gpqa · z 0.19 · q 1.00
hle · hle · z 0.01 · q 1.00
Multi-step constraints59.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 1.12 · q 1.00
Evidence integration & verification45.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z -1.00 · q 1.00
MMLU-ProV3 evidence
LMSpeed rank#7
Score88.2%
UpdatedSep 13, 2026
Confidence4
GPQAV3 evidence
LMSpeed rank#95
Score81.2%
UpdatedSep 13, 2026
Confidence4
HLEV3 evidence
LMSpeed rank#102
Score15.0%
UpdatedSep 13, 2026
Confidence4
AA-LCRV3 evidence
LMSpeed rank#83
Score55.3
UpdatedSep 10, 2026
Confidence3
CritPtV3 evidence
LMSpeed rank#65
Score1.4
UpdatedSep 10, 2026
Confidence3
Reasoning score
LMSpeed rank#50
Score59.0
UpdatedSep 10, 2026
Confidence3

Knowledge

V3.0

undefined metric} other undefined metrics}} · Provisional

Score53.780% interval39.7–67.71/4 Measured dimensionsArtificial Analysis Intelligence Index17.9#92 / 117AA-GPQA Diamond81.2#75 / 113
Dimensions and evidence
Broad knowledge53.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z -0.03 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z 0.41 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#92
Score17.9
UpdatedSep 10, 2026
Confidence3
AA-GPQA Diamond
LMSpeed rank#75
Score81.2
UpdatedSep 10, 2026
Confidence3
AA-HLE
LMSpeed rank#79
Score15.0
UpdatedSep 10, 2026
Confidence3
AA-Omniscience Accuracy
LMSpeed rank#23
Score45.8
UpdatedSep 10, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#11
Score92.4
UpdatedSep 10, 2026
Confidence3
Knowledge scoreV3 evidence
LMSpeed rank#25
Score76.6
UpdatedSep 10, 2026
Confidence3
GPQA Diamond (Vals)
LMSpeed rank#25
Score87.9
UpdatedSep 10, 2026
Confidence3
MMLU-Pro (Vals)
LMSpeed rank#15
Score88.6
UpdatedSep 10, 2026
Confidence3

Math

V3.0

undefined metric} other undefined metrics}} · Provisional

Score51.580% interval35.4–67.61/4 Measured dimensionsMath score50.2#36 / 63FrontierMath v2 (Tiers 1-3)35.6#16 / 47
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs51.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z -0.22 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.33 · q 1.00
Applied & tool-assisted mathPrior only
Math score
LMSpeed rank#36
Score50.2
UpdatedSep 10, 2026
Confidence3
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#16
Score35.6
UpdatedAug 20, 2026
Confidence1
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#24
Score4.2
UpdatedAug 20, 2026
Confidence1

Multilingual

V3.0

undefined metric} other undefined metrics}} · Provisional

Score58.580% interval41.5–75.51/4 Measured dimensionsAA Global-MMLU-Lite92.7#2 / 5
Dimensions and evidence
Cross-language understanding58.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
global_mmlu · aa_global_mmlu_lite · z 1.35 · q 0.63
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
AA Global-MMLU-LiteV3 evidence
LMSpeed rank#2
Score92.7
UpdatedSep 10, 2026
Confidence3

Multimodal

V3.0

undefined metric} other undefined metrics}} · Provisional

Score50.980% interval34.5–67.21/4 Measured dimensionsAA-MMMU-Pro78.6#19 / 68Design Arena Website1210.0#46 / 78
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoning50.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
benchlm_category_multimodal · benchlm_category_multimodal_grounded · z 0.39 · q 1.00
Video & grounded actionPrior only
AA-MMMU-Pro
LMSpeed rank#19
Score78.6
UpdatedSep 10, 2026
Confidence3
Design Arena Website
LMSpeed rank#46
Score1210.0
UpdatedSep 10, 2026
Confidence3
Multimodal Grounded scoreV3 evidence
LMSpeed rank#19
Score75.8
UpdatedSep 10, 2026
Confidence3

Instruction following

V3.0

undefined metric} other undefined metrics}} · Provisional

Score47.980% interval31.9–63.91/4 Measured dimensionsAA-IFBench55.1#53 / 84Instruction Following score66.2#46 / 52
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization47.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z -0.57 · q 1.00
Multi-turn & long instructionsPrior only
AA-IFBenchV3 evidence
LMSpeed rank#53
Score55.1
UpdatedSep 10, 2026
Confidence3
Instruction Following score
LMSpeed rank#46
Score66.2
UpdatedSep 10, 2026
Confidence3

Pricing Comparison

Compare Gemini 3 Flash API pricing across 445 providers. Prices range from $0.0014/M to $480.00/M. MyDamoxing offers the lowest rate at $0.0014/M. 15 providers offer free API credits or a free tier.

ProviderHealthModel VariantGroupInput ($/M)Output ($/M)Speed (t/s)First tokenAudit
L1
0%
L2
0%
gemini-3-flash
默认分组
$5.47/M
Cache read$0.547/M
$27.38/M
269.2 t/s
4.31 s
L1
100%
gemini-3-flash
default
-20%$0.400/M
Cache read$0.040/M
-20%$2.40/M
187.3 t/s
6.13 s
L1
100%
gemini-3-flash-preview
default
-20%$0.400/M
Cache read$0.040/M
-20%$2.40/M
L1
100%
gemini-3-flash-preview-nothinking
OFC
$300.00/M
$1200.00/M
L1
100%
gemini-3-flash-preview
default
$1.46/M
Cache read$0.730/MImage$14.60/MAudio in$0.117/M
$14.60/M
166.3 t/s
4.34 s
L1
0%
gemini-3-flash-preview
default
$0.0050/request
-
159.7 t/s
7.44 s
L1
0%
gemini-3-flash
default
$0.0060/request
-
L1
99%
gemini-3-flash
default
$8.00/request
-
157.2 t/s
6.59 s
L1
99%
gemini-3-flash-preview
default
$8.00/request
-
L1
99%
gemini-3-flash-preview-nothinking
default
$8.00/request
-
L1
99%
gemini-3-flash-preview-maxthinking
default
$8.00/request
-
L1
100%
gemini-3-flash-preview
Cli-Gemini-1
-98%$0.011/M
Cache read$0.0011/M
-98%$0.065/M
156.9 t/s
7.99 s
L1
28%
gemini-3-flash-preview
Gemini特价
$0.0048/request
-
152.2 t/s
5.94 s
L1
61%
gemini-3-flash-preview
default
$0.010/request
-
146.1 t/s
8.32 s
L1
61%
google/gemini-3-flash
default
$0.010/request
-
L1
61%
gemini-3-flash
default
$0.010/request
-
L1
61%
cli/gemini-3-flash-preview
default
$0.010/request
-
L1
61%
anti/gemini-3-flash-preview
default
$0.010/request
-
L1
99%
gemini-3-flash-preview
default
$0.800/M
$4.80/M
118.3 t/s
9.59 s
L1
99%
gemini-3-flash
default
$0.800/M
$4.80/M
Showing 20 model IDs of 182.

Alternatives & Similar Models

Frequently Asked Questions

What benchmark data does Gemini 3 Flash include?
LMSpeed shows Gemini 3 Flash benchmark context, API price, output speed, first-token latency, and provider data across 460 providers when those signals are available.
What is the Gemini 3 Flash API price?
Gemini 3 Flash has pricing from undefined provider} other undefined providers}}, ranging from $0.0014/M to $480.00/M. MyDamoxing has the lowest listed price.
What does the Gemini 3 Flash API pricing table include?
The Gemini 3 Flash API pricing table compares 460 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
Which provider has the cheapest Gemini 3 Flash API pricing?
MyDamoxing currently has the lowest listed Gemini 3 Flash price at $0.0014/M across undefined provider} other undefined providers}}.
Can I compare Gemini 3 Flash API price and speed together?
Yes. LMSpeed shows Gemini 3 Flash API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
Is Gemini 3 Flash API free?
Yes, Gemini 3 Flash free API options are available through 15 providerundefined other undefined} on LMSpeed, including 兔子API, DeadlySignal API, DeadlySignal API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
Where can I get Gemini 3 Flash free API access?
LMSpeed currently lists 15 free API providerundefined other undefined} for Gemini 3 Flash: 兔子API, DeadlySignal API, DeadlySignal API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.

Also known as

Gemini-3-Flash-PreviewNotion/gemini-3-flash-preview[91VIP]/gemini-3-flash-preview[K]/gemini-3-flash-preview[ba]q|假流式/gemini-3-flash-preview

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.

Build with LMSpeed Data

Free

Free public API for LLM pricing, benchmarks & provider data

  • Real-time pricing & availability
  • Speed & latency benchmarks
  • 300+ models, 600+ providers
  • 1,000 requests/day
View API Documentation