modelbenchmark.io

Gemini 3.6 Flash

Google · gemini-3-6-flash

Compare

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Specification

google listing

Context
1M
Max output
66K
Released
2026-07-21
Knowledge cutoff
2026-03
Retires
2026-11-19
Open weights
no
Input
text, image, video, audio, pdf
Output
text

Price

US dollars per million tokens · google list price

Input
$0.75
Output
$3.75
Cache read
$0.075
Cache write
$0.0417

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputvertex_ai$0.375
Batch outputvertex_ai$1.875
Priority inputdatabricks$1.35
Priority outputdatabricks$6.75

Batch input is 50% below the interactive input price at the same listing.

Rate limits

as listed

Requests per minute
2,000
Tokens per minute
800,000

Quality

9 benchmarks · 2 sources

Composite
68th
percentile of 344 scored models
Rank
111 / 344
±0.08 sd
Evidence
9 × 2
3 or more benchmarks, from 2 or more sources
Effort range
10.6
points between effort settings
reasoning80th3/4 bench
math66th3/7 bench
knowledge87th1/1 bench
general39th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
low84th4
minimal78th4
high76th9

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SimpleQA Verified66.2 ±1.5highEpoch AI2026-08-27
GPQA diamond94.1 ±1.4highEpoch AI2026-08-02
↳86.4 ±2.4lowEpoch AI2026-08-06
↳85.9 ±2.5minimalEpoch AI2026-08-07
Settings differ by 8.2 points on this benchmark.
OTIS Mock AIME 2024-202594.2 ±3.1highEpoch AI2026-08-02
↳82.2 ±5.8lowEpoch AI2026-08-07
↳80.0 ±6.0minimalEpoch AI2026-08-07
Settings differ by 14.2 points on this benchmark.
Chess Puzzles42.0 ±5.0lowEpoch AI2026-10-13
↳40.0 ±4.9highEpoch AI2026-10-13
↳29.0 ±4.6minimalEpoch AI2026-10-13
Settings differ by 13.0 points on this benchmark.
FrontierMath-Tiers-1-3-v259.0 ±2.9highEpoch AI2026-08-02
Mystery Game Puzzles30.0 ±4.6highEpoch AI2026-08-05
↳25.0 ±4.4minimalEpoch AI2026-08-05
↳23.0 ±4.2lowEpoch AI2026-08-05
Settings differ by 7.0 points on this benchmark.
LiveBench74.5high · 23 runsLiveBench2026-06-25
FrontierMath-Tier-4-v221.9 ±6.5highEpoch AI2026-08-02
Furniture Assembly23.3 ±5.4highEpoch AI2026-09-10

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 39 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$0.75$3.75$0.075—1M66K—
kenari$0.3429$1.7143$0.0343$0.01711M66K—
kilo$0.375$1.875$0.0375$0.02081M66K—
abacus$0.75$3.75$0.075—1M66K—
aihubmix$0.75$3.75$0.075—1M66K—
cortecs$0.75$3.75$0.075$0.0381M66K—
crossmodel$0.75$3.75$0.075$0.751M66K—
databricks$0.75$3.75$0.075$0.751M66K—
edenai$0.75$3.75$0.075$0.04171M66K—
gemini$0.75$3.75$0.075—1M66K—
github-copilot$0.75$3.75$0.075—1M64K—
google-vertex$0.75$3.75$0.075—1M66K—
impossibl$0.75$3.75$0.075—1M66K—
llmgateway$0.75$3.75$0.075$0.08331M66K—
llmgateway-providers · google-ai-studio$0.75$3.75$0.075$0.08331M66K—
llmgateway-providers · google-vertex$0.75$3.75$0.075$0.08331M66K—
nano-gpt$0.75$3.75$0.075$0.04171M66K—
ofox$0.75$3.75$0.075$0.04151M66K—
openrouter$0.75$3.75$0.075$0.04171M66K—
orcarouter$0.75$3.75$0.075—1M66K—
tempr$0.75$3.75$0.075—1M66K—
vercel$0.75$3.75$0.075—1M64K—
vertex_ai$0.75$3.75$0.075—1M66K2026-11-19
vertex_ai-language-models$0.75$3.75$0.075—1M66K2026-11-19
poe$0.7576$3.7879$0.0758—1M66K—
venice$0.9375$4.6875$0.0938—1M66K—
kyma · kyma$1.013$5.063$0.1012—1M8K—
302ai$1.50$7.50$0.15—1M66K—
aimlapi$1.50$7.50$0.15—1M66K—
cloudflare-ai-gateway$1.50$7.50$0.15$1.501M66K—
commandcode$1.50$7.50$0.15—1M66K—
merge-gateway$1.50$7.50$0.15—1M66K—
neon$1.50$7.50$0.15—1M66K—
opencode$1.50$7.50$0.15—1M66K—
perplexity$1.50$7.50$0.15————
perplexity-agent$1.50$7.50$0.15—1M66K—
prime$1.50$7.50——1M66K—
requesty$1.50$7.00$0.15—1M66K—
sap-ai-core————1M66K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02abacusCache read$0.15
2026-10-22abacusCache read$0.075
2026-09-02crossmodelCache read$0.15
2026-09-05crossmodelCache read$0.075
2026-09-02impossiblCache read$0.15
2026-10-22impossiblCache read$0.075
2026-09-02openrouterCache read$0.075
2026-09-06openrouterCache read$0.075
2026-10-10openrouterCache read$0.075
2026-09-02orcarouterCache read$0.15
2026-10-22orcarouterCache read$0.075
2026-09-02crossmodelCache write$1.50
2026-09-05crossmodelCache write$0.75
2026-09-02openrouterCache write$0.0417
2026-09-19openrouterCache write$0.0417
2026-10-10openrouterCache write$0.0417
2026-09-02abacusInput$1.50
2026-10-22abacusInput$0.75
2026-09-02crossmodelInput$1.50
2026-09-05crossmodelInput$0.75
2026-09-02impossiblInput$1.50
2026-10-22impossiblInput$0.75
2026-09-02kenariInputfree
2026-10-22kenariInput$0.3429
2026-09-02openrouterInput$0.75
2026-09-06openrouterInput$0.75
2026-10-10openrouterInput$0.75
2026-09-02orcarouterInput$1.50
2026-10-22orcarouterInput$0.75
2026-09-02abacusOutput$7.50
2026-10-22abacusOutput$3.75
2026-09-02crossmodelOutput$7.50
2026-09-05crossmodelOutput$3.75
2026-09-02impossiblOutput$7.50
2026-10-22impossiblOutput$3.75
2026-09-02kenariOutputfree
2026-10-22kenariOutput$1.7143
2026-09-02openrouterOutput$3.75
2026-09-06openrouterOutput$3.75
2026-10-10openrouterOutput$3.75
2026-09-02orcarouterOutput$7.50
2026-10-22orcarouterOutput$3.75
2026-09-06databricksCache read$0.1875
2026-10-29databricksCache read$0.075
2026-09-06databricksCache write$1.875
2026-10-29databricksCache write$0.75
2026-09-06databricksInput$1.875
2026-10-29databricksInput$0.75
2026-09-06databricksOutput$9.375
2026-10-29databricksOutput$3.75
2026-09-22aihubmixCache read$0.15
2026-10-22aihubmixCache read$0.075
2026-09-22aihubmixInput$1.50
2026-10-22aihubmixInput$0.75
2026-09-22aihubmixOutput$7.50
2026-10-22aihubmixOutput$3.75
2026-10-13aimlapiCache read$0.195
2026-10-23aimlapiCache read$0.15
2026-10-13aimlapiInput$1.95
2026-10-23aimlapiInput$1.50
2026-10-13aimlapiOutput$9.75
2026-10-23aimlapiOutput$7.50

More from Google

most-hosted first