Pass IndexThe State of AISign in

Gemini 3.8 Flash

Gemini 3.8 Flash is the high-efficiency, cost-effective powerhouse of the Gemini 3 family.

text + image + video + file → text · made by Google

$0.75→$3.75per Mtok in / out
Databricks · 10 sellers

Sold by 32 ways

SellerLaneRate
Google Vertex AI cloudbatch$0.38per Mtok in$1.88per Mtok outraw.githubusercontent.com · read 2026-10-31
Google Vertex AI cloudflex$0.38per Mtok in$1.88per Mtok outraw.githubusercontent.com · read 2026-10-31
Databricks cloudstandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$0.75per Mtok cache writeraw.githubusercontent.com · read 2026-10-31
Google Vertex AI cloudstandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$3.75per Mtok out, reasoningmodels.dev · read 2026-10-31
Google Vertex AI cloudpriority$1.35per Mtok in$6.75per Mtok out$0.14per Mtok cachedraw.githubusercontent.com · read 2026-10-31
Databricks cloudpriority$1.35per Mtok in$6.75per Mtok out$0.14per Mtok cachedraw.githubusercontent.com · read 2026-10-31
Nous Research 2 ways$0.82per Mtok in$4.12per Mtok out$0.000001per image$0.083per Mtok cached$0.042per Mtok cache write
Nous Research aggregatorbatch$0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.042per Mtok cache writeinference-api.nousresearch.com · read 2026-09-20
Nous Research aggregatorstandard$0.82per Mtok in$4.12per Mtok out$0.000001per image$0.083per Mtok cached$0.042per Mtok cache writeinference-api.nousresearch.com · read 2026-10-29
OpenRouter 8 ways$0.82per Mtok in$4.12per Mtok out$0.000001per image$0.083per Mtok cached$0.042per Mtok cache write
OpenRouter aggregatorbatch$0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-09-20
OpenRouter aggregatorgoogle-ai-studio/flex$0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.021per Mtok cache writeopenrouter.ai · read 2026-09-20
OpenRouter aggregatornot on the seller's list todaygoogle-vertex/global/flex$0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.021per Mtok cache writeopenrouter.ai · read 2026-09-22
OpenRouter aggregatorgoogle-ai-studio$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-09-20
OpenRouter aggregatorgoogle-vertex/global$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-09-20
OpenRouter aggregatorstandard$0.82per Mtok in$4.12per Mtok out$0.000001per image$0.083per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-10-16
OpenRouter aggregatorgoogle-vertex/us$0.82per Mtok in$4.12per Mtok out$0.083per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-10-16
OpenRouter aggregatorgoogle-ai-studio/priority$1.35per Mtok in$6.75per Mtok out$0.14per Mtok cached$0.075per Mtok cache writeopenrouter.ai · read 2026-09-20
OpenRouter aggregatorgoogle-vertex/global/priority$1.35per Mtok in$6.75per Mtok out$0.14per Mtok cached$0.075per Mtok cache writeopenrouter.ai · read 2026-09-20
AtlasCloud aggregatorstandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedapi.atlascloud.ai · read 2026-09-20
ElectronHub aggregatorstandard$0.75per Mtok in$3.75per Mtok outapi.electronhub.ai · read 2026-10-31
GitHub Copilot aggregatorstandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-10-31
Google 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
Google aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
Requesty aggregatorvertex$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedrouter.requesty.ai · read 2026-09-20
Requesty aggregatornot on the seller's list todaystandard$0.82per Mtok in$4.12per Mtok out$0.083per Mtok cachedmodels.dev · read 2026-09-03
Vercel AI Gateway aggregatorstandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedai-gateway.vercel.sh · read 2026-09-20
google-vertex 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
google-vertex aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
kilo 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
kilo aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
llmgateway 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
llmgateway aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
llmgateway-providers 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
llmgateway-providers aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
merge-gateway 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
merge-gateway aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
nano-gpt 0 ways$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached
nano-gpt aggregatornot on the seller's list todaystandard$0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-03
Venice AI aggregatorstandard$0.94per Mtok in$4.69per Mtok out$0.094per Mtok cachedmodels.dev · read 2026-10-31
opencode 0 ways$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cached
opencode aggregatornot on the seller's list todaystandard$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cachedmodels.dev · read 2026-09-03

Measured 61 standings

PlaceBoardMetricScore
2ndof 69Deepswe — Epoch AIPass@1 (high)0.738
5thof 326GPQA Diamondmean_score (high)95.391
5thof 56Humanity's Last Exam (Epoch AI replication)Accuracy44.52
6thof 298ARC-AGI-1 (Semi-Private)Score (%) (high)98.5
8thof 309Arc agi — Epoch AIScore (high)98.5
8thof 50Design Arena · godotgamedev (agents)Elo1273
8thof 34Design Arena · pdf (agents)Elo1273
8thof 14Frontiermath erdos — Epoch AImean_score (high)0
8thof 414LMArena · TextScore (Elo) (high)1497
8thof 93Simpleqa verified — Epoch AImean_score (high)69.7
9thof 35Blueprint bench 2 — Epoch AIScore38.612
9thof 39Design Arena · blender3d (agents)Elo1194
9thof 18Rli — Epoch AIScore5.83
9thof 29Surface evolver bench — Epoch AIMean score (high)0.769
12thof 60Apex agents — Epoch AIPass@1 score0.643
14thof 163Artificial Analysis · Coding IndexIndex76.3
14thof 154Chess puzzles — Epoch AImean_score (high)58
14thof 165LMArena · VisionScore (Elo) (high)1289
15thof 68Design Arena · mobileapps (agents)Elo1234
15thof 173Weirdml — Epoch AIAccuracy (high)84.81
16thof 61Design Arena · fullstack (agents)Elo1244
16thof 114Design Arena · svg (models)Elo1295
16thof 21Frontierswe — Epoch AIScore (high)19.627
16thof 142Mystery game puzzles — Epoch AImean_score (high)47
18thof 25Weirdml v3 — Epoch AIScore (high)7.379
20thof 298ARC-AGI-2 (Semi-Private)Score (%) (high)89.17
20thof 290Arc agi 2 — Epoch AIScore (high)89.167
20thof 93Design Arena · asciiart (models)Elo1271
20thof 157Design Arena · uicomponent (models)Elo1315
20thof 30Mirrorcode — Epoch AImean_score (high)38.889
21stof 68Design Arena · webapps (agents)Elo1229
22ndof 56Gdp pdf — Epoch AIGDP.pdf score (medium)0.234
23rdof 306OTIS Mock AIME 2024-2025mean_score (high)98.889
24thof 282ARC-AGI-2 (Public Eval)Score (%) (high)92.5
25thof 273ARC-AGI-1 (Public Eval)Score (%) (high)98
25thof 163Design Arena · codecategories (models)Elo1302
25thof 46Frontiercode — Epoch AIMain score (medium)0.412
25thof 35Furniture assembly — Epoch AImean_score (high)31.667
26thof 169Design Arena · website (models)Elo1299
28thof 162Design Arena · gamedev (models)Elo1304
29thof 41Design Arena · python-pptxslides (agents)Elo1139
30thof 141LMArena · WebDevScore (Elo) (high)1583
31stof 135Webdev arena — Epoch AIArena Score (high)1567.88
32ndof 150Design Arena · 3d (models)Elo1293
32ndof 122Frontiermath tiers 1 3 v2 — Epoch AImean_score (high)68.421
33rdof 131Artificial Analysis · Agentic IndexIndex40.2
33rdof 71Vending bench 2 — Epoch AIScore5093.793
35thof 112ARC-AGI-3 (Semi-Private)Score (%) (high)10.37
35thof 41Design Arena · spreadsheet (agents)Elo1057
36thof 84Proofbench — Epoch AIAccuracy48
37thof 154Design Arena · dataviz (models)Elo1276
37thof 235Dtbench — Epoch AIAccuracy95.72
37thof 53LMArena · AgentNet Improvement (%)2.75
39thof 235Scicode — Epoch AIScore (high)56.597
40thof 132Ale bench — Epoch AIPerformance (high)1269.72
41stof 86Artificial Analysis · Intelligence IndexArtificial Analysis Intelligence Index (high)31
41stof 54Design Arena · androidnative (agents)Elo1083
44thof 82Cursorbench — Epoch AIScore (high)39.6
51stof 197Lmca — Epoch AIScore (medium)52.9
54thof 78Frontiermath tier 4 v2 — Epoch AImean_score (high)21.951
73rdof 260Critpt — Epoch AIAccuracy (high)18.286

About

Gemini 3.8 Flash — a text model from Google, sold by 10 companies from $0.75 in and $3.75 out per million tokens, placed 5th of 326 on GPQA Diamond.

It takes text, images, video and files and returns text, with a context window of 1,048,576 tokens. It was published in September 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Ten companies sell it. The cheapest is $0.75 in and $3.75 out per million tokens at Databricks. Beside the standard rate there are faster, batch, flex, separately routed and regional lanes. It has been measured on 61 boards, and stands best at 5th of 326 on GPQA Diamond.

Every current figure

Maker
Google
Register
model
Takes
text + image + video + file
Returns
text
Context
1,048,576 tokens
Published
September 2026
Licence
not read
Sellers
10
Price
$0.75 in and $3.75 out per million tokens — Databricks
Boards
61
Best place
5th of 326 — GPQA Diamond

Known as 2 names

google/gemini-3.8-flashvertex/gemini-3.8-flash