Google: Gemini 2.5 Flash-Lite

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

gemini-2.5-flash-lite

AvailableGoogleChatCached input 90% less

Input / Output-50%: $0.10 / $0.40$0.05 / $0.20
Context: 1M
Max output: 64K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

About Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is Google's fastest and most budget-friendly multimodal model in the Gemini 2.5 family. It takes text and images, supports tool calls, schema-constrained JSON and prompt caching, and is meant for simple requests sent in very large numbers, such as classification, tagging and quick agent steps. Google lists it as previous generation.

Where it works well

Google calls it the fastest and most budget-friendly multimodal model of the 2.5 family, which fits traffic where each call is simple.
It reads images as well as text, so cheap image tagging, captioning and screenshot triage need no separate vision model.
Response schemas and tool calling work, so it can feed clean JSON to downstream code or direct requests inside an agent.
Prompt caching rewards workloads that reuse a long instruction block across many short inputs.

When to choose another model

Quality on multi-step reasoning, long analysis and difficult code is below gemini-2.5-flash, which is the better pick when answers need depth.
Google marks the 2.5 models as previous generation and recommends 3.5 Flash-Lite for new projects.
It produces text only, with no image, speech or live-audio output.

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-2.5-flash-lite:generateContent

API format:

curl "https://api.tokenlab.sh/v1beta/models/gemini-2.5-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 $0.10 / Output $0.40 / Cache read $0.01
Verified price: Input $0.05 / Output $0.20 / Cache read $0.005
Discount: -50%

Prompt cache pricing

Cache read

Official price: $0.01
Verified price: $0.005
Discount: -50%

Tool fees

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

Search grounding

Official price: $0.035/req
Verified price: $0.0175/req
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $0.10 / Output $0.40 / Cache read $0.01	Input $0.05 / Output $0.20 / Cache read $0.005	-50%
Prompt cache pricing
Cache read	$0.01	$0.005	-50%
Tool feesCharged per call, only when the model uses the tool.
Search grounding	$0.035/req	$0.0175/req	-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 10, 2026, 11:49 PM UTC

30-day success rate: 100.0%
30-day requests: 100+
Last active: 6 days ago

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

Open in Console

Open Gemini 2.5 Flash-Lite in Console with a prompt ready to edit or send.

Help me try gemini-2.5-flash-lite with a short message at /v1beta/models/gemini-2.5-flash-lite:generateContent. Show the reply, latency, and cost.

Use cases

Best for

Reasoning
Vision

Content moderation and tagging
Label user posts, images or product listings against a fixed rubric at high volume and return the label as JSON.
Intent routing
Classify an incoming message and pick the right handler or tool before a larger model sees it.
Bulk captions and alt text
Write a one-line description for each image in a product library, keeping a consistent style from a cached instruction.
Low-stakes summaries
Produce short digests of emails, tickets or chat threads where a rough gist is enough.

Prompt examples

Classify this support message as billing, bug, feature request or other, and return only the label as JSON.

Write alt text under 15 words for each of these product photos, naming color and material.

Read this receipt image and return merchant name and total as JSON; use null for anything you cannot read.

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 2.5 Flash-Lite designed for?

Cheap, quick handling of simple requests at scale. Google describes it as the fastest and most budget-friendly multimodal model in the 2.5 family. Classification, tagging, extraction from clear inputs and routing are its typical jobs.

When should I use Flash instead of Flash-Lite?

Use gemini-2.5-flash when the task needs reasoning across several steps, longer analysis or more reliable code. Use Flash-Lite when prompts are short and the answer is easy to check. A common pattern is Lite first, with failures retried on Flash.

Can Gemini 2.5 Flash-Lite process images?

Yes. Images and text can go in the same request. It works for tagging, short captions and reading simple documents, but dense or ambiguous images benefit from a larger model.

Does it support structured output?

Yes. Response schema, JSON mode and tool use are supported. Provide the schema in the request and the model returns JSON that follows it, which is useful for pipelines that parse results automatically.

Should new projects start on Gemini 2.5 Flash-Lite?

Google's model list says 2.5 models are previous generation and points new projects to 3.5 Flash-Lite. This model still works for existing integrations, but a new build should evaluate the newer Flash-Lite first.

How much does Gemini 2.5 Flash-Lite cost?

On TokenLab, Gemini 2.5 Flash-Lite costs Input $0.05 / Output $0.20 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 2.5 Flash-Lite?

Gemini 2.5 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 2.5 Flash-Lite use?

Use https://api.tokenlab.sh/v1beta/models/gemini-2.5-flash-lite:generateContent for Gemini 2.5 Flash-Lite. The request example below shows the matching code shape.

Which operations does Gemini 2.5 Flash-Lite support?

Gemini 2.5 Flash-Lite supports Text to text. Select an operation above to see its endpoint and request example.