Google: Gemini 3.8 Flash

Google: Gemini 3.8 Flash is a large language model from Google. It costs $0.750 per million input tokens and $3.75 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierimage inputvideo inputfile inputaudio input

Input / 1M tokens: $0.750
Output / 1M tokens: $3.75
Cached input / 1M: $0.075
Context window: 1.0M

This model also charges $0.014 per search request

That is $14.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0026, so the search fee is 5.3× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

2 hosts serve Gemini 3.8 Flash. Same weights, same API - the price difference is pure margin and routing.

Providers serving Google: Gemini 3.8 Flash, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
Google AI StudioCheapest	$0.375	$1.88	1.0M	-	99.8%
Google	$0.375	$1.88	1.0M	-	92.5%

The spread between Google AI Studio and Google is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 41.2
Coding index: 76.3
Agentic index: 41.1

About Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Specifications

Google: Gemini 3.8 Flash specifications
Model ID	`google/gemini-3.8-flash`
Provider	Google
Context window	1.0M tokens
Max output	66K tokens
Input modalities	text, image, video, file, audio
Output modalities	text
Knowledge cutoff	-
Open weights	No
Released	September 2, 2026

Cheaper alternatives

Models that cost less than Gemini 3.8 Flash while keeping at least half its context window and every input modality it supports.

Gemini 3 Flash Preview

$0.500 in · $3.00 out

1.3× cheaper

Gemini 3.5 Flash Lite

$0.300 in · $2.50 out

1.8× cheaper

Gemini 2.5 Flash

$0.300 in · $2.50 out

1.8× cheaper

Gemini 3.1 Flash Lite

$0.250 in · $1.50 out

2.7× cheaper

Gemini 3.1 Flash Lite Preview

$0.250 in · $1.50 out

2.7× cheaper

Frequently asked

How much does Google: Gemini 3.8 Flash cost?

$0.750 per million input tokens and $3.75 per million output tokens. Cached input reads cost $0.075 per million tokens.

What is the context window of Google: Gemini 3.8 Flash?

1.0M tokens, with up to 66K tokens of output per request.

Does Google: Gemini 3.8 Flash have extra fees beyond per-token pricing?

Yes. Google: Gemini 3.8 Flash charges $0.014 per search request - $14.00 per 1,000 requests - on top of $0.750 per million input tokens and $3.75 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 5.3× the token cost.

Which provider serves Google: Gemini 3.8 Flash cheapest?

Google AI Studio at $0.375 per million input tokens - about the same cheaper than Google, the most expensive of the 2 hosts serving it.

Confirm against the source: Google official pricing.