Google: Gemini 3.8 Flash

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

Compare models

gemini-3.8-flash

AvailableGoogleChatCached input 90% less

Input / Output-50%: $0.75 / $3.75$0.375 / $1.88
Context: 1M
Released: Sep 2, 2026
Max output: 64K
Modalities: VisionChat
Capabilities: Tool usePrompt Cache

About Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model and the newest in the Gemini 3 line, released in September 2026. Google describes it as engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows, and recommends it for new projects. It reads text and images, thinks, calls tools, returns JSON, and caches context.

Where it works well

Aimed at long-horizon software engineering, where an agent works through many steps without losing the thread.
Thinking support for planning and debugging before it acts.
Tool calling suits autonomous agents and enterprise workflows with many integrations.
Text and images in one prompt, with schema-bound JSON output and context caching.

When to choose another model

Flash-Lite models respond faster for simple, high-volume tasks.
Gemini 3.1 Pro may still be preferred when a task rewards its Pro-tier reasoning.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textGemini API

POST/v1beta/models/gemini-3.8-flash:generateContent

API format:

curl "https://api.tokenlab.sh/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello!"}]}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $0.75 / Output $3.75 / Cache read $0.075
Verified price: Input $0.375 / Output $1.88 / Cache read $0.0375
Discount: -50%

Prompt cache pricing

Cache read

Official price: $0.075
Verified price: $0.0375
Discount: -50%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.014/search
Verified price: $0.007/search
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $0.75 / Output $3.75 / Cache read $0.075	Input $0.375 / Output $1.88 / Cache read $0.0375	-50%
Prompt cache pricing
Cache read	$0.075	$0.0375	-50%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.014/search	$0.007/search	-50%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 16, 2026, 11:08 AM UTC

30-day success rate: 99.8%
7-day median latency: 14.2sn=2,016
7-day P95 latency: 154.2sn=2,016
30-day requests: 3K+
Last active: 6 minutes ago

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Gemini 3.8 Flash in Console with a prompt ready to edit or send.

Help me try gemini-3.8-flash with a short message at /v1beta/models/gemini-3.8-flash:generateContent. Show the reply, latency, and cost.

Use cases

Best for

Vision

Autonomous coding agents
Hand it a repository task and let it plan, edit, run commands, and check the results.
Enterprise workflows
Drive multi-system processes such as onboarding or claims handling through tool calls.
Long research tasks
Gather material across many documents and keep earlier decisions in view while new sources are added to the task.
Replacing older Flash models
Move existing 3.5 to 3.7 Flash traffic to it when quality gains justify the change.

Prompt examples

Fix the flaky checkout test in this repo: find the cause, patch it, run the suite, and report what changed.

Process this new-employee request: create accounts, assign the standard groups, and write the confirmation email.

Read the 12 attached reports and track which conclusions change as new data appears.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Gemini 3.8 Flash?

Google's newest and, by its own description, most intelligent Flash model. It targets long software tasks, autonomous agents, and complex enterprise workflows, with image input, tools, and thinking.

Is Gemini 3.8 Flash a stable release?

Yes. Google lists it as stable and, together with 3.5 Flash-Lite, names it as a model to start new projects on, so it is a safe target for production integrations.

How is it different from 3.7 Flash?

3.8 is the later generation and carries the explicit long-horizon engineering and enterprise focus; 3.7 targets complex coding and reliable multi-step execution. Re-run your evaluation before switching.

Does it replace Gemini 3.1 Pro?

Not automatically. Pro remains the reasoning-first tier of the Gemini line. Try 3.8 Flash first for agent and coding work and keep Pro for tasks where it clearly scores better.

How much does Gemini 3.8 Flash cost?

On TokenLab, Gemini 3.8 Flash costs Input $0.375 / Output $1.88 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Gemini 3.8 Flash?

Gemini 3.8 Flash accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens in one response.

Which endpoint should Gemini 3.8 Flash use?

Use https://api.tokenlab.sh/v1beta/models/gemini-3.8-flash:generateContent for Gemini 3.8 Flash. The request example below shows the matching code shape.

Which operations does Gemini 3.8 Flash support?

Gemini 3.8 Flash supports Text to text. Select an operation above to see its endpoint and request example.