Google

Gemini 3.8 Flash API Pricing 2026

Compare pricing, benchmarks, and providers for Gemini 3.8 Flash. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Gemini 3.8 Flash was released on September 2, 2026. Pricing starts at $0.750 per million input tokens and $3.75 per million output tokens. The model supports a context window of up to 1.0M tokens. API access is available through Google.

Context Window
1.0M
tokens
Pricing
Input$0.750
Output$3.75
Cached$0.075
per 1M tokens
Speed
Output123 tok/s
TTFT16.43s
median latency
Capabilities
VisionAudio InToolsCaching

Gemini 3.8 Flash is priced at $0.750 per million input tokens and $3.75 per million output tokens. It has a context window of 1,048,576 tokens. It is available from 3 providers, with Google AI Studio the cheapest at $0.750 per million input tokens (input prices range from $0.750 to $0.825). It runs at roughly 123 tokens per second with a 16.43s time to first token. On benchmarks, Gemini 3.8 Flash scores Intelligence 30.8 (59th percentile), GPQA 95.3 (98th percentile). Over the past ~90 days its cheapest input price has risen 100%, from $0.375 to $0.750 per million tokens.

Pricing Comparison

Compare Gemini 3.8 Flash with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.750
$3.750
—
—
95.3
1,048,576
Try
$0.700
$1.400
—
—
—
131,072
Try
$0.700
$1.400
—
—
—
-
Try
$0.700
$2.100
—
—
—
1,048,576
Try
$0.720
$0.720
—
—
—
131,072
Try
$0.740
$2.960
—
—
—
256,000
Try
$0.750
$1.200
—
—
—
131,072
Try
$0.750
$0.800
—
41.6
2.0
131,072
Try
$0.750
$3.750
—
—
—
1,048,576
Try
$0.750
$3.750
—
—
—
1,048,576
Try
$0.750
$3.750
—
—
—
1,048,576
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Gemini 3.8 Flash is available from multiple providers with different pricing and availability.

3
Providers
$0.750
Cheapest Input/M
$3.750
Cheapest Output/M
Google AI Studio
Best Price

Provider Pricing

3 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Google AI Studio
Google AI Studio
Best Price
$0.750
$3.750
$0.075
$0.042
100.0%
Google
Google
Best Price
$0.750
$3.750
$0.075
$0.042
100.0%
$0.825
$4.125
$0.083
$0.042
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Gemini 3.8 Flash perform? Vote based on your experience.

Cost vs. Quality

Compare Gemini 3.8 Flash's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Detailed Benchmark Scores

Intelligence
30.8 (59th pct)
Coding
-
Math
-
MMLU Pro
-
GPQA
95.3 (98th pct)
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Gemini 3.8 Flash

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Gemini 3.8 Flash directly in your browser.

Open Playground

Frequently Asked Questions

Gemini 3.8 Flash costs $0.000750 per 1,000 input tokens and $0.003750 per 1,000 output tokens.
Gemini 3.8 Flash is available from 3 providers. Google AI Studio offers the best price.
Google AI Studio offers Gemini 3.8 Flash at $0.750 per million input tokens, the lowest of 3 providers (input prices range from $0.750 to $0.825 per million tokens).
Gemini 3.8 Flash scores Intelligence 30.8 (59th percentile), GPQA 95.3 (98th percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for Gemini 3.8 Flash has increased 100%, from $0.375 to $0.750 per million tokens.
We compare Gemini 3.8 Flash with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Google Models

See pricing for all Google models.

View all Google models →