Google

Gemini 3.8 Flash

Name: Gemini 3.8 Flash
Brand: Google
Price: 1.013 USD
Availability: InStock

Google's newest Flash tier, generally available since September 2, 2026 — the same 1M-token context and 64K output ceiling as 3.7 Flash, at the same list rate, with Google's largest Flash-to-Flash gains on software engineering and agentic tasks.

Modalities

Text+Image → Text

Below release

Not established

Weights

Not published

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#36/71

$1.013

output $5.063

median $1.013 · best $0.0494

Price · output#43/70

$5.063

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#36/54

99.15%

353 observations since 2026-09-03

median 99.9% · best 100.0%

Throughput#41/65

31 tok/s

probe median, one fixed prompt

median 35.7 tok/s · best 365.1 tok/s

Response time#26/65

2.19 s

probe median, to a complete answer

median 2.96 s · best 0.89 s

Context

1.05M

max output 65,536

published by Google, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#42

of 101 active models

Tokens served

3.6M

all-time

Platform share

0.1%

of all tokens

Tokens · last 14 daysSep 26 → Oct 9

How it behaves under real clients

The same model answering different prompt shapes — measured, not benchmarked.

Client	Requests	Tokens	Throughput	To first token	p95 total	Completed
Node.js App	240	666.7K	19 tok/s	8.72 s	20 s	97.1%
Python App	169	626.6K	17 tok/s	6.90 s	23 s	99.4%

Grouped by the client that sent the request. Not a benchmark: the same model on different prompt shapes. Throughput and time-to-first-token are medians; p95 is the slowest response in twenty.

Two clocks, and why they disagree

Kyma measures this model twice. Both are real; they answer different questions.

Probe · every 6h · 30 days

2.19s to answer

One fixed prompt, on a schedule, to every model. Comparable, because the model is the only thing that changes.

Observations: 353
Answered by a substitute: 3

Real traffic · last 7 days

8.72s to answer

Your requests, at the lengths clients actually send. Not comparable between models, but it is what running this one feels like.

Requests: 41
Completed: 100%
p95: 18.8 s

The gap is prompt length, not the model degrading. Use the probe figure to choose between models, the traffic figure to budget for your own.

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$1.013$2.026 /1M input$5.063$10.126 /1M output

50% off· ends Dec 31Returns to $2.026 /1M input and $10.126 /1M output on Dec 31.

Hobby10 req/day · 2K in / 500 out

~$1.37/mo

Production1,000 req/day · 2K in / 500 out

~$137/mo

Scale20,000 req/day · 2K in / 500 out

~$2,735/mo

+ Estimate your workload

Requests / day1,000

Input tokens / request2,000

Output tokens / request500

Estimated monthly cost

$137

$4.56 / day on Gemini 3.8 Flash

Same workload on:

Gemini 3.5 Flash Lite$74.92-45%

Gemini 3.1 Pro$405+196%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

When to use Gemini 3.8 Flash

Updated 2026-09-03

Where this model earns its cost — and where it doesn't.

Gemini 3.8 Flash is Google's September 2026 Flash-tier release. It accepts text, image, audio, video and file input and returns text, with reasoning, tool calling and structured outputs on one request. Google's model card puts the knowledge cutoff at March 2026.

Against 3.7 Flash the shape is unchanged — 1,048,576 tokens of context and 65,536 tokens of output — and the difference is quality: Google positions it as its most intelligent Flash model, with the biggest gains on software engineering, long-horizon agentic work and multimodal understanding.

On Kyma it serves through an OpenAI-compatible endpoint with automatic failover to a second independent route. Prompt caching is supported and repeated prefixes bill at this model's cached input rate. Every response carries the exact request cost in usage.cost and names the model that answered in the X-Kyma-Model header.

Agentic coding at Flash cost

Multi-step tool use over a large repository, with reasoning and structured outputs, at the Flash tier's price and latency.

Long-form structured extraction

Reads a 1M-token corpus and emits tens of thousands of tokens of schema-constrained JSON in a single response.

Whole-document translation and rewriting

The 64K output ceiling fits an entire long document's rewritten text without splitting the job into chunks.

Multimedia review

Takes video, audio, images and files alongside a text prompt and returns a long written analysis in one pass.

Not ideal for: Do not reach for this when a short reply is all you need and cost is the deciding factor — the cheaper Flash tiers answer the same short prompts, and the large output ceiling buys nothing you will use.

How it compares

Against the peers people actually weigh it against.

Spec	Gemini 3.8 Flash	Gemini 3.5 Flash Lite	Gemini 3.1 Pro
Input /1M	$1.013	$0.405	$2.70
Output /1M	$5.063	$3.375	$16.20
Context	1M	1M	1M
Tools	Yes	Yes	Yes
Reasoning	Yes	Yes	Yes
Throughput	31 tok/s	45 tok/s	96 tok/s

Quick start

Up and running in under two minutes.

1
Create an API key
Sign up and grab a key from the dashboard. Gemini 3.8 Flash needs a top-up — the signup credit covers the free tier.
Get API key →

Make your first request

Drop in your key and send a chat completion — fully OpenAI-compatible.

curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'

Stream responses

Add "stream": true to receive tokens as they arrive.

curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Gemini 3.8 Flash?

Gemini 3.8 Flash has a 1M-token context window — roughly 1542 pages of text in a single request.

How much does the Gemini 3.8 Flash API cost?

$1.013 per 1M input tokens and $5.063 per 1M output tokens (on offer until Dec 31, then $2.026/$10.126). No subscription; you pay only for what you use.

Does Gemini 3.8 Flash support function calling?

Yes — Gemini 3.8 Flash supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Gemini 3.8 Flash publicly available?

No. Google does not publish Gemini 3.8 Flash's weights — it is reachable through an API rather than as a file you can download and run (https://deepmind.google/models/model-cards/gemini-3-8-flash/, read 2026-09-03). That is Google's decision about their own product, not a limitation of Kyma.

Is Gemini 3.8 Flash ever served below the precision its creator released it at?

Kyma cannot say, and for this model nobody can. Google does not publish Gemini 3.8 Flash's weights, so there is no released checkpoint whose precision a route could be measured against. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use Gemini 3.8 Flash?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to gemini-3.8-flash. Signing up is free, but this model needs a top-up: the $0.50 signup credit covers the free tier only.

How is this different from Gemini 3.7 Flash?

Same context (1M tokens), same output ceiling (64K), same input set and same list price. The difference is the model itself: Google reports its largest Flash-to-Flash gains on software engineering and agentic tasks. If 3.7 Flash already does the job, nothing forces a move; new work should start on 3.8.

Is the current price permanent?

No. Google publishes a launch rate through December 31, 2026 and a higher list rate after that; the Pricing table on this page shows the promotional rate, the date it is promised through, and the list rate it returns to.

Does prompt caching work on this model?

Yes. Repeated prompt prefixes bill at this model's cached input rate, and the saving is reported per request in usage.cache_discount.

Needs a top-up — the signup credit covers the free tier.Create account →

More models by Google

See all 13 →

Model	Context	Input	Output
Lyria 3.5	—	$0.108 / song
Gemini 3.5 Transcribe	—	$0.00675 / min
Gemini 3.7 Flash	1M	$1.013	$5.063
Gemini 3.6 Flash	1M	$1.013	$5.063
Gemini 3.5 Flash Lite	1M	$0.405	$3.375
Gemini 3.5 Flash	1M	$1.928	$11.563
Gemma 4 31B	128K	$0.0763	$0.218
Nano Banana 3 Flash	—	$0.061 / image