Google

Gemini 3.8 Flash

CTX1.05M

93Quality

Reasoning · Vision · Tools

Input$0.75/M

Output$3.75/M

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

PaidProprietary992/1040

Drag to turn

GoogleTextUncommon

Gemini 3.8 Flash

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

gemini-3.8-flash

Type: Text
Quality: 93 · Top 7% on the Epoch Capabilities Index
Context window: 1,048,576 tokens
Max output: 65,536 tokens
Input price: $0.75 / 1M tokens
Output price: $3.75 / 1M tokens
Cache read: $0.075 / 1M tokens
Cache write: —
Released: Sep 2, 2026
Knowledge cutoff: —
Takes in: Text, Image, Audio, Video, PDF
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Uncommon
Set number: 992/1040

Open Google docs Quality 93 Where to run it 30 Evolution 6/6 Meet its creature Battle Qwen3.6 27B

Weights aren’t public. Use is governed by Google’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: ai.google.dev.

How good is it?

Public leaderboard scores for Gemini 3.8 Flash, refreshed daily from Epoch AI and LMArena.

Top 7% of the 277 models on the Epoch Capabilities Index: #19.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#19 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.157.2 index
LMArena Text#8 of 416
People compare two anonymous answers and vote for the better one.1,499 rating
Listed as Gemini 3.8 Flash (High)
LMArena Text · Coding#16 of 411
The text arena’s coding prompts only.1,507 rating
Listed as Gemini 3.8 Flash (High)
LMArena Text · Math#5 of 400
The text arena’s math prompts only.1,527 rating
Listed as Gemini 3.8 Flash (High)
LMArena Text · Creative writing#7 of 414
The text arena’s creative writing prompts only.1,492 rating
Listed as Gemini 3.8 Flash (High)
LMArena WebDev#31 of 144
Each model builds a web app from the same prompt; people pick the better one.1,585 rating
Listed as Gemini 3.8 Flash (High)
LMArena Vision#8 of 165
Questions about images, voted by people.1,314 rating
Listed as gemini-3.8-flash-high

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

30 providers sell Gemini 3.8 Flash through an API. Prices are per million tokens, cheapest first.

Cheapest302.AI$0.75 in · $3.75 out
From the labGoogle$0.75 in · $3.75 out

API providers

Provider	Input	Output	Context
302.AICheapest paid`gemini-3.8-flash`	$0.75	$3.75	1.05M
AIHubMix`gemini-3.8-flash`	$0.75	$3.75	1.05M
CrossModel`gemini/gemini-3.8-flash`	$0.75	$3.75	1.05M
DevPass (LLM Gateway)`gemini-3.8-flash`	$0.75	$3.75	1.05M
GitHub Copilot`gemini-3.8-flash`	$0.75	$3.75	1M
GoogleOfficial`gemini-3.8-flash`	$0.75	$3.75	1.05M
Kilo Gateway`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
LLM Gateway`google-vertex/gemini-3.8-flash`	$0.75	$3.75	1.05M
Merge Gateway`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
NanoGPT`google/gemini-3.8-flash`	$0.75	$3.75	1.05M

Show 20 more providers

Provider	Input	Output	Context
NEAR AI Cloud`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
Ofox`google/gemini-3.8-flash`	$0.75	$3.75	1M
Prime Inference`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
Requesty`gemini-3.8-flash`	$0.75	$3.75	1.05M
Standard Compute`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
Tempr Gateway`google/gemini-3.8-flash`	$0.75	$3.75	1.05M
Vercel AI Gateway`google/gemini-3.8-flash`	$0.75	$3.75	1M
Vertex`gemini-3.8-flash`	$0.75	$3.75	1.05M
Vivgrid`gemini-3.8-flash`	$0.75	$3.75	1.05M
Poe`google/gemini-3.8-flash`	$0.76	$3.79	1.05M
Cortecs`gemini-3.8-flash`	$0.82	$4.13	1.05M
OpenRouter`google/gemini-3.8-flash`	$0.82	$4.13	1.05M
Opper`gemini-3.8-flash`	$0.82	$4.13	1.05M
Venice AI`gemini-3-8-flash`	$0.94	$4.69	1M
AI/ML API`google/gemini-3-8-flash`	$0.97	$4.88	1.05M
CommandCode`google/gemini-3.8-flash`	$1.50	$7.50	1M
Eden AI`google/gemini-3.8-flash`	$1.50	$7.50	1.05M
Neon`gemini-3-8-flash`	$1.50	$7.50	1.05M
OpenCode`gemini-3.8-flash`	$1.50	$7.50	1.05M
SAP AI Core`gemini-3.8-flash`	—	—	1.05M

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

Gemini 3.8 Flash

Gemini 3.8 Flash

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Face off

More from Google

Gemini 4 Argon

embeddinggemma-2

timesfm-3.0-pytorch

Gemini 3.7 Flash

Gemini 3.6 Flash

Gemini 3.5 Flash Lite

Nano Banana 2 Lite

Gemini Omni Flash Preview