Google: Gemini 3.5 Flash-Lite

google/gemini-3.5-flash-lite

Fastest, most cost-effective model in the 3.5 family, optimized for high-throughput agentic tasks, translation, and simple data processing.

ModalitiesTextImageVideoAudioFileText

In / out price$0.120 / $1.00 per 1M

Context1.05M

Released—

Providers

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

Provider	Input /M	Output /M	Cache read /M	Latency	Throughput
Google	$0.120	$1.00	$0.030	2.88s	263 tps

Capabilities (22)

StreamingTool callingParallel tool callsStructured outputReasoningThinkingSystem promptVisionVideo InputAudio InputPDF inputPrompt cachingCode executionComputer useFile SearchSearch GroundingMaps GroundingUrl ContextBatchFlex InferencePriority InferenceStop sequences

Supported parameters (14)

temperaturetop_ptop_kmax_output_tokensstop_sequencesstreamtoolstool_configresponse_mime_typeresponse_schemathinking_levelmedia_resolutionsafety_settingsresponse_format

Any other parameter you send is ignored rather than rejected.

Pricing

What this model costs to run, next to the rate it is posted at. Caching and discounts mean the price actually paid is often below the listed one.

Effective input price

$0.120

/M tokens · listed $0.300

Effective output price

$1.00

/M tokens · listed $2.50

Rate	Listed	Charged	Unit
Input	$0.300	$0.120	per 1M tokens
Output	$2.50	$1.00	per 1M tokens
Cache read	$0.030	$0.030	per 1M tokens
Cache write	$0.300	$0.300	per 1M tokens

UTC

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better). Throughput and TTFT are measured on streaming requests, which are the only ones with a first-token moment to time.

Throughput

263tok/s

P50, streaming requests

Latency

2.88s

P50, end to end

UTC

Throughput

P993949 tok/s

P951219 tok/s

P50267 tok/s

Latency

P503399ms

P756609ms

P9519.1s

P9954.0s

Time to first token

P501284ms

P958628ms

Cache hit rate

0.66%

Share of input tokens served from the prompt cache over the window.

Availability

The share of requests to this model that completed successfully. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Success rate (30d)

93.10%

over 133,791 requests

Days with traffic

of the last 30

Days are UTC days. Days with no requests are omitted rather than drawn at 100% — no traffic is not evidence of availability.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.Oxyy Tester91.6K tokens

Activity

Token volume and request traffic to this model over time. Daily totals, UTC.

Prompt880.3M

Reasoning8.7K

Completion40.9M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Frequently asked questions

What is Gemini 3.5 Flash-Lite?

Fastest, most cost-effective model in the 3.5 family, optimized for high-throughput agentic tasks, translation, and simple data processing.

How much does Gemini 3.5 Flash-Lite cost?

Gemini 3.5 Flash-Lite costs $0.300 per million input tokens and $2.50 per million output tokens. Cached prompt tokens are billed at $0.030 per million. You pay per request, with no subscription.

What is the context length of Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite has a context window of 1,048,576 tokens, and can return up to 65,536 tokens in one response.

Does Gemini 3.5 Flash-Lite support tool calling and structured outputs?

Yes — Gemini 3.5 Flash-Lite supports both tool calling and structured outputs.

What inputs and outputs does Gemini 3.5 Flash-Lite support?

Gemini 3.5 Flash-Lite accepts text, image, video, audio, file as input and returns text.

What other models does Google have?

Google also offers Gemini 2.5 Flash, Gemini 2.5 Flash-Lite, Gemini 2.5 Flash TTS, Gemini 2.5 Pro through Oxyy.

When was Gemini 3.5 Flash-Lite released?

No release date is published for Gemini 3.5 Flash-Lite.

Explore more models

Browse the full catalog Models Compare pricing Pricing

More models from Google

Gemini 2.5 FlashGoogle's first hybrid reasoning model with configurable thinking budgets; best price-performance for low-latency, high-…text · 1.05M context · $0.300 / $2.50 Gemini 2.5 Flash-LiteSmallest and most cost-effective multimodal model in the 2.5 family, built for at-scale usage.text · 1.05M context · $0.100 / $0.400 Gemini 2.5 Flash TTSFast and controllable text-to-speech for low-latency, cost-efficient applications and real-time assistants, with fine c…audio tts · 8K context · $0.500 / —Gemini 2.5 ProMost advanced model of the 2.5 family, with deep reasoning and coding capability for complex tasks.text · 1.05M context · $1.25 / $10.00 Gemini 2.5 Pro TTSHigh-fidelity speech synthesis optimized for quality in structured workflows such as podcasts and audiobooks, with more…audio tts · 8K context · $1.00 / —Nano Banana 2High-efficiency production-scale image generation and editing, balancing speed with 4K generation, world knowledge and…image generation · — context · $0.500 / $3.00

Provider

Input /M

Output /M

Cache read /M

Latency

Throughput

Google

$0.120

$1.00

$0.030

2.88s

263 tps

Rate

Listed

Charged

Unit

Input

$0.300

$0.120

per 1M tokens

Output

$2.50

$1.00

per 1M tokens

Cache read

$0.030

per 1M tokens

Cache write

$0.300

per 1M tokens