Model facet · Pricing

Gemini 3.8 Flash Pricing: 2026 and 2027 Rates

Standard rates through 31 December 2026: $0.75 input and $3.75 output per million tokens. Cache storage is $0.50 per million tokens per hour; cached input reads cost $0.075 per million, a 90% discount. Rates double on 1 January 2027.

Published token rates

TierInput / 1M tokensOutput / 1M tokensEffective date
Standard$0.75$3.75Now through 31 Dec 2026
Standard$1.50$7.50From 1 Jan 2027
Batch$0.375$1.875Now through 31 Dec 2026
Flex$0.375$1.875Now through 31 Dec 2026
Priority$1.35$6.75Now through 31 Dec 2026

Caching economics

Cache componentRate
Cached input read$0.075 per 1M tokens (90% discount)
Cache storage$0.50 per 1M tokens per hour through 31 Dec 2026
Cache storage$1.00 per 1M tokens per hour from 1 Jan 2027

Cost per completed task, not per token

At high reasoning Gemini 3.8 Flash costs $0.58 per Artificial Analysis index task versus $0.40 for Gemini 3.7 Flash. The per-token rate is identical; the cost-per-task difference comes from 3.8 spending about 30% more output tokens. At low reasoning the cost drops to about $0.24 per task. Use the rate card for forecasting, the cost-per-task number for budgeting.

Ready to test the workflow?

Create account & add credits

The 1 January 2027 price step is dated and checkable

Every cost model built on today's price expires on 1 January 2027. Input doubles from $0.75 to $1.50 per million; output doubles from $3.75 to $7.50. Batch, flex and priority tiers double at the same time. Build pricing comparisons with both columns and revisit in late 2026.

Frequently asked questions

Can I run Gemini 3.8 Flash on OneInfer?

Yes. Gemini 3.8 Flash is served on OneInfer via OpenRouter under the model identifier google/gemini-3.8-flash. Point the OpenAI-compatible base URL at https://api.oneinfer.ai/v1/ula and pass your OneInfer API key in the Authorization header.

How much does Gemini 3.8 Flash cost per million tokens?

$0.75 per million input tokens and $3.75 per million output tokens through 31 December 2026. Cached input reads are $0.075 per million.

When does Gemini 3.8 Flash pricing change?

1 January 2027. Standard input rises to $1.50 per million and output to $7.50 per million. Batch, flex and priority tiers double at the same time.

How much does Gemini 3.8 Flash cost per completed task?

About $0.58 per Artificial Analysis index task at high reasoning and about $0.24 at low reasoning, compared with $0.40 for Gemini 3.7 Flash at its default tier.

Put Gemini 3.8 Flash to work

Fund a controlled evaluation, send a reference frame or document, and measure quality and cost on your own workload.