Google: Gemini 3.1 Flash-Lite

Low-latency Gemini model for high-volume multimodal and agent workloads

gemini-3.1-flash-lite

AvailableGoogleChatCached input 90% less

Input / Output-50%: $0.25 / $1.50$0.125 / $0.75
Context: 1M
Released: May 7, 2026
Max output: 64K
Modalities: VisionChat
Capabilities: Tool usePrompt Cache

About Gemini 3.1 Flash-Lite

Gemini 3.1 Flash-Lite is Google's low-latency, low-cost model in the Gemini 3.1 line, built for high-volume multimodal and agent workloads. Google describes frontier-class performance rivaling larger models at a fraction of the cost. It reads text and images, calls tools, returns schema-bound JSON, and supports context caching, and it sits below the Flash tier in capability.

Where it works well

Short response times make it fit for interactive features where each call must return quickly.
Images and text go into the same request, which suits receipt, form, and screenshot processing.
Schema-bound JSON output removes the need for brittle parsing of free text.
Tool calling and context caching support repeated, similar agent steps at scale.

When to choose another model

For long, multi-step coding agents the Flash and Pro models hold up better than a Lite model.
It is not a reasoning-first model; hard math or deep planning is better sent to Gemini 3.1 Pro.

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-3.1-flash-lite:generateContent

API format:

curl "https://api.tokenlab.sh/v1beta/models/gemini-3.1-flash-lite: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 $0.25 / Output $1.50 / Cache read $0.025
Verified price: Input $0.125 / Output $0.75 / Cache read $0.0125
Discount: -50%

Prompt cache pricing

Cache read

Official price: $0.025
Verified price: $0.0125
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 $0.25 / Output $1.50 / Cache read $0.025	Input $0.125 / Output $0.75 / Cache read $0.0125	-50%
Prompt cache pricing
Cache read	$0.025	$0.0125	-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 Nov 1, 2026, 6:33 AM UTC

30-day success rate: 100.0%
30-day requests: 100K+
Last active: 2 minutes ago

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

Open in Console

Open Gemini 3.1 Flash-Lite in Console with a prompt ready to edit or send.

Help me try gemini-3.1-flash-lite with a short message at /v1beta/models/gemini-3.1-flash-lite:generateContent. Show the reply, latency, and cost.

Use cases

Best for

Vision

Bulk extraction
Pull fields from thousands of invoices or forms and write each result as a validated JSON object.
Content moderation and tagging
Label user uploads and comments against a fixed policy with a one-line justification.
Routing layer
Decide which specialist model or tool a request should go to, then pass it on.
Real-time assistants
Power autocomplete, quick replies, or voice-assistant turns where a visible wait would hurt the experience of the person using it.

Prompt examples

Extract vendor, date, total, and currency from this invoice image and return them as JSON.

Tag the comment below as spam, abuse, question, or praise and explain the choice in one sentence.

Given this user message, pick one of: search_docs, create_ticket, answer_directly. Reply with the tool name only.

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 3.1 Flash-Lite best for?

High-volume, latency-sensitive jobs such as extraction, classification, tagging, routing, and quick multimodal answers. It trades some depth of reasoning for speed and a lighter load per call.

Does it accept images?

Yes. Text and images can be mixed in one request, so it can read documents, screenshots, and photos. Its answer comes back as text or as JSON that matches your schema.

Can it call tools?

Yes. Function calling is supported, which lets it act as the first-stage agent that picks tools for simple requests or forwards hard cases to a larger model.

How is it different from Gemini 3.5 Flash-Lite?

3.5 Flash-Lite is the newer generation and the one Google now points new projects toward; 3.1 Flash-Lite is the older Lite model, still stable. Test your own prompts on both before moving traffic.

How much does Gemini 3.1 Flash-Lite cost?

On TokenLab, Gemini 3.1 Flash-Lite costs Input $0.125 / Output $0.75 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 3.1 Flash-Lite?

Gemini 3.1 Flash-Lite accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens in one response.

Which endpoint should Gemini 3.1 Flash-Lite use?

Use https://api.tokenlab.sh/v1beta/models/gemini-3.1-flash-lite:generateContent for Gemini 3.1 Flash-Lite. The request example below shows the matching code shape.

Which operations does Gemini 3.1 Flash-Lite support?

Gemini 3.1 Flash-Lite supports Text to text. Select an operation above to see its endpoint and request example.