Roboflow
Google

Google: Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite Overview

Gemini 3.5 Flash-Lite is a natively multimodal reasoning model developed by Google DeepMind, released on July 21, 2026 as part of the Gemini 3.5 model family. It is the fastest model in the 3.5 series, designed for both low-latency tasks and high-throughput production workloads such as agentic search, document processing, receipt translation, and large-scale data extraction. The model accepts text, images, audio, and video as inputs, with a context window of up to 1 million tokens, and produces text output. It supports configurable thinking levels, allowing developers to tune the balance between response quality, cost, and latency depending on workload requirements.

On agentic and coding benchmarks, Gemini 3.5 Flash-Lite significantly outperforms its predecessor, Gemini 3.1 Flash-Lite, including on Terminal-Bench 2.1 (54% vs. 31%), GDM-MRCR v2 long-context (72.2% vs. 60.1%), and real-world task execution as measured by GDPval-AA v2 (1140 vs. 642). It also surpasses Gemini 3 Flash on SWE-Bench Pro (54.2% vs. 49.6%) and OSWorld-Verified (74.0% vs. 65.1%). According to the Artificial Analysis Index, the model generates output at approximately 350 tokens per second. It is built on the Gemini 3.5 Flash foundation and is evaluated across reasoning, coding, multimodal understanding, multilingual performance, and long-context tasks. The model is developed under Google's Frontier Safety Framework.

Gemini 3.5 Flash-Lite Interactive Demo

Model settings

Thinking level

Max output tokens

Default 65,536 · max 65,536

Sign in to adjust thinking and output length per run.

Results appear here. Add an image or pick an example to run Gemini 3.5 Flash-Lite.

Gemini 3.5 Flash-Lite Details & Performance

Details

Resources

—

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRObject DetectionVideo ClassificationVision LanguageVisual Question Answering

Features

Foundation VisionLLMs with Vision CapabilitiesMultimodal Vision

Usage

Past 30 Days

Performance

Avg. Latency

Gemini 3.5 Flash-Lite Vision Evals

Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across five vision tasks, and answers are scored against ground truth.

Evals updated October 13, 2026Pricing updated October 19, 2026

Overall score#33 of 63
61.7%
Avg cost / sample#20 of 63
$0.0014
Avg speed / sample#3 of 63
3.92s
Avg tokens / sample
1.6K

Strengths and weaknesses

Gemini 3.5 Flash-Lite averages 61.7% across the five Vision Evals tasks, ranking #33 of 63 models overall.

Its weakest relative showing is Counting, ranking #44 of 63 at 52.7%.

At $0.0014 per sample it is the 20th cheapest of the 63 benchmarked models, and its average inference time of 3.9s per sample makes it the 3rd fastest.

Performance profile

Field medianGemini 3.5 Flash-Lite

Field medians: Object Detection 54.4%, Counting 63.5%, Identification 84.4%, OCR 63.6%, Reasoning 57.6%.

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
57.5%
#27 of 63$0.00234.09s
Counting
52.7%
#44 of 63$0.00071.68s
Identification
84.4%
#31 of 63$0.00041.23s
OCR (low)
65.8%
#20 of 47$0.00124.65s
Single value
64.3%
Transcription
87.5%
Structured JSON
75.8%
Text localization
31.9%
OCR (high)
71.2%
#15 of 47$0.00639.60s
Single value
66.1%
Transcription
88.6%
Structured JSON
82.1%
Text localization
46.4%
Reasoning (low)
48.3%
#40 of 63$0.00122.38s
Reasoning (high)
68.9%
#26 of 50$0.00425.82s
  • Thinking longer helps: 5.4 points higher on ocr at high effort for 5.3x the cost and 2.1x the latency.
  • Thinking longer helps: 20.5 points higher on reasoning at high effort for 3.4x the cost and 2.4x the latency.

Price vs. performance

Score vs. cost

Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.

62 models on the current benchmark · scores and efficiency pooled across all five tasks at low effort · Gemini 3.5 Flash-Lite highlighted

Gemini 3.5 Flash-Lite scores are from a single run per task; a three-run re-run under the current protocol is pending · Methodology

View all Vision Evals →

Gemini 3.5 Flash-Lite Pricing

Gemini 3.5 Flash-Lite costs $0.300 per 1M input tokens and $2.50 per 1M output tokens.

Input$0.300 / 1M tokens
Output$2.50 / 1M tokens
Cached input$0.030 / 1M tokens

Pricing updated Oct 19, 2026

Alternatives to Gemini 3.5 Flash-Lite

Other models worth comparing for similar use cases.

OpenAI
GPT-6 Luna
GPT-6 Luna is the fast, cost-efficient tier of OpenAI's GPT-6 model family, sitting below GPT-6 Sol and the larger GPT-6 Astra model that opened the generation. It is a proprietary multimodal transformer that accepts text and image input and returns text, and it exposes an adjustable reasoning effort setting so the same model can run in a low-latency mode or spend additional inference compute on harder problems. OpenAI positions it for high-volume and latency-sensitive workloads such as conversational assistants, classification, and lightweight agentic pipelines, while noting that at higher reasoning effort it handles software engineering and computer-use tasks that previously required a Sol-tier model.The model supports a context window of roughly 1,050,000 input tokens with a maximum output of 128,000 tokens, which allows long documents, extended agent traces, and large code repositories to be processed in a single request. OpenAI describes the GPT-6 generation as improving factual reliability and adopting a more concise communication style relative to the GPT-5.6 series, and attributes the efficiency of the Sol and Luna tiers to gains in caching and inference rather than to reduced capability. Architecture details, parameter counts, and training data are not published.
Anthropic
Claude Haiku 5.5
Claude Haiku 5.5 is a proprietary multimodal language model from Anthropic and the smallest member of the Claude 5.5 family, released on October 7, 2026 after Claude Opus 5.5 and Claude Sonnet 5.5. It accepts text and image input and returns text, with a 1M token context window and up to 128K output tokens per request. It is the first Haiku-class model with an adjustable effort parameter: adaptive thinking is on by default and the model decides how much to reason, steered by effort levels from low to max with medium as the default. Its training data cutoff is June 2026. Pricing starts at $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100K tokens, which Anthropic reports is about 90% lower than Claude Haiku 4.5 for requests in that range.Anthropic positions Haiku 5.5 for high-volume, latency-sensitive work such as classification, extraction, routing, summarization, and subagent tasks, and describes it as its fastest model to date at standard speed. On visual and agentic evaluations reported at launch, it scores 46.4% on Chartography, a chart reading benchmark, compared with 6.4% for Haiku 4.5 and 61.6% for Sonnet 5.5, and 72.4% on the offline subset of OSWorld 2.1, a screenshot driven computer use benchmark, compared with 15.7% for Haiku 4.5. It uses the same tokenizer as Claude Opus 4.7 and later models, so the same text counts as roughly 30% more tokens than on Haiku 4.5.
OpenAI
GPT-5.6 Luna
GPT-5.6 Luna is the fastest and most cost-efficient model in OpenAI's GPT-5.6 family, which also includes Sol (the flagship tier) and Terra (the balanced mid-tier). Introduced under a new naming convention where the generation number (5.6) and a durable capability tier name (Luna, Terra, Sol) together define each model, Luna occupies the lightweight end of the family and is designed for high-volume, latency-sensitive workloads such as summarization, drafting, autocomplete, classification, and routine automation. The GPT-5.6 family as a whole advances capabilities in software engineering, computer use, professional knowledge work, scientific research, and cybersecurity, with all three tiers rated at the "High" capability level under OpenAI's Preparedness Framework for both cybersecurity and biological/chemical risk domains.GPT-5.6 Luna supports multimodal input and function calling, and shares the family's 1.5 million token context window. On Terminal-Bench 2.1, Luna scores 82.5%, and on the Artificial Analysis Coding Agent Index it outperforms comparable models at roughly one-quarter the estimated cost of higher-tier alternatives. Luna supports the GPT-5.6 prompt caching scheme, which introduces explicit cache breakpoints and a 30-minute minimum cache life. The model was previewed on June 26, 2026 to a limited group of trusted partners via the OpenAI API and Codex, with general availability rolling out on July 9, 2026 across ChatGPT, Codex, and the API.
Qwen
Qwen3.5 9b
Qwen3.5-9B is a 9-billion-parameter multimodal foundation model developed by Alibaba Cloud's Qwen team, released on March 2, 2026 as part of the Qwen3.5 model family. Designed for efficient multimodal reasoning and long-context language tasks, it notably outperforms the older Qwen3-30B, a model more than three times its size, on key benchmarks including GPQA Diamond, IFEval, and LongBench.The model supports vision-language inputs through an early-fusion multimodal architecture built on a dense hybrid foundation of Gated Delta Networks and Gated Attention. It can also operate in a text-only mode by skipping the vision encoder during inference. It provides a 262,144-token context window (extensible to ~1M tokens via YaRN) and is released under the Apache License 2.0. Within the current AI landscape, Qwen3.5-9B offers a strong balance of capability and efficiency, making it well-suited for multimodal assistants, document analysis, long-context reasoning, and developer-deployed agentic systems.
Qwen
Qwen3 VL 8B Instruct
Qwen3 VL 8B Instruct is an open-weight multimodal vision-language model developed by Qwen / Alibaba Cloud as part of the Qwen3-VL series, designed for instruction-following tasks that combine text with visual inputs such as images and video. Released around October 2025 under the Apache-2.0 license, it targets developers who need capable multimodal reasoning without the scale or cost of very large models.The model contains roughly 8.8 billion dense parameters and supports text, image, and video understanding with strong spatial perception, visual reasoning, and emerging visual agent abilities such as GUI interaction. A standout feature is its native ~256K token context window, extendable to around 1M tokens, enabling long-document reading and extended video comprehension. In today’s landscape, it balances openness, long-context capacity, and solid multimodal performance against heavier proprietary models. Typical applications include multimodal assistants, document and video analysis, visual question answering, and research or product prototyping where transparency and deployability matter.

Other Google Gemini Flash-Lite models

Other versions in the same family as Gemini 3.5 Flash-Lite.

GoogleGemini 3.1 Flash-LiteGoogleGemini 2.5 Flash-Lite

Deploy Gemini 3.5 Flash-Lite with an API

Gemini 3.5 Flash-Lite runs as a hosted REST endpoint through Roboflow Workflows. Pick a task, then hand the prompt to your coding agent or copy the code. Deploying the workflow into a free Roboflow workspace replaces the your-workspace and YOUR_API_KEY placeholders with your own.

Connect your agent to Roboflow (once)

Add the Roboflow MCP server

claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp

Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.

Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).

Deploy this workflow to your Roboflow workspace to use it.

Integrate the Roboflow "Gemini 3.5 Flash-Lite" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/gemini-3-5-flash-lite-captioning
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value }, `model_api_key`: my provider key } }.

With the Roboflow MCP connected, call `workflows_get` on "gemini-3-5-flash-lite-captioning" to read the exact input schema and treat it as the source of truth. A live `workflows_run` for this workflow also needs my Google AI Studio key (`model_api_key`) passed as a runtime parameter; if you don't have it yet, skip the test run — it will fail with a server error without the provider key, which is expected and not a problem with your code — and rely on the schema. Validate the real run via the REST call once the keys below are set. Without the MCP, use the contract above.

Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
- `GOOGLE_API_KEY` (sent as `model_api_key`) from https://aistudio.google.com/apikey — my Google AI Studio key
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.

Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.
Installpip install inference-sdk

Deploy this workflow to your Roboflow workspace to use it.

# 1. Import the library
from inference_sdk import InferenceHTTPClient

# 2. Connect to your workflow
client = InferenceHTTPClient(
  api_url="https://serverless.roboflow.com",
  api_key="YOUR_API_KEY"
)

# 3. Run your workflow on an image
result = client.run_workflow(
  workspace_name="your-workspace",
  workflow_id="gemini-3-5-flash-lite-captioning",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  parameters={
    "model_api_key": "YOUR_GOOGLE_API_KEY"
  },
  use_cache=True  # cache workflow definition for 15 minutes
)

# 4. Get your results
print(result)

Deploy this workflow to your Roboflow workspace to use it.

const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/gemini-3-5-flash-lite-captioning', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    api_key: 'YOUR_API_KEY',
    inputs: {
      "image": {"type": "url", "value": "IMAGE_URL"},
      "model_api_key": "YOUR_GOOGLE_API_KEY"
    }
  })
});

const result = await response.json();
console.log(result);

Deploy this workflow to your Roboflow workspace to use it.

curl --location 'https://serverless.roboflow.com/your-workspace/workflows/gemini-3-5-flash-lite-captioning' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"},
    "model_api_key": "YOUR_GOOGLE_API_KEY"
  }
}'

Gemini 3.5 Flash-Lite License

Proprietary

Gemini 3.5 Flash-Lite is proprietary: the weights are not distributed, and the Gemini 3.5 Flash-Lite license is the vendor's commercial terms of service that you accept when you call the API.

Commercial use
Permitted under the vendor terms, typically metered per token or per request, with the vendor usage policy applying to your inputs and outputs.
Modification
Not available. Gemini 3.5 Flash-Lite weights are closed, so you can configure prompts and use vendor-hosted fine-tuning where it is offered, but you cannot modify the model itself.
Redistribution
Not permitted. You cannot self-host or resell the model; you build on the hosted API instead.

Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.

Do I need a commercial license for Gemini 3.5 Flash-Lite?

Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy an open model instead of Gemini 3.5 Flash-Lite, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.

Do not hesitate to reach out with questions for your commercial project — our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

This model is proprietary. The author retains all rights, and use of the model is governed by their specific terms of service or license agreement.

Commercial use depends on the terms set by the model author. Most proprietary commercial models require a paid subscription, API key, or per-call billing. Check the provider’s pricing and terms-of-service for details.

License information is provided as a guide and is not legal advice.

Frequently Asked Questions About Gemini 3.5 Flash-Lite Vision

Yes. Gemini 3.5 Flash-Lite accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is OCR at 65.8% (#20 of 47 at low effort). You can test it on your own image in the demo above.

Yes. it scores 65.8% (#20 of 47 at low effort) on Vision Evals OCR, which covers single readings, full transcriptions, structured JSON, and locating text with boxes. Within that, full transcriptions score 87.5%, and returning the fields of a label or form as JSON scores 75.8%.

Not its strength. On Vision Evals, Gemini 3.5 Flash-Lite scores 57.5% mAP@50 on object detection (#27 of 63 at low effort) and 52.7% judge-graded accuracy on object counting. For production counting or precise localization, pairing it with a specialized detector like RF-DETR or your own trained model in a Roboflow Workflow is usually more reliable: detect the objects, then count the detections.

On our benchmark's task mix, Gemini 3.5 Flash-Lite averages $0.0014 per sample at $0.30 per 1M input and $2.50 per 1M output tokens (#20 of 63 on cost), with an average speed of 3.9s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Gemini 3.5 Flash-Lite sits #33 of 63 at 61.7%, just behind Qwen3.5 35B-A3B (62.5%) and just ahead of Muse Glimmer 30B (61.4%). See the full side-by-side: Gemini 3.5 Flash-Lite vs Qwen3.5 35B-A3B.