Roboflow
Google

Google: Gemini 3.5 Flash

Gemini 3.5 Flash Overview

Gemini 3.5 Flash is a multimodal language model developed by Google DeepMind and released at Google I/O 2026. It is built on the Gemini 3 Flash reasoning foundation and introduces configurable thinking levels (minimal, low, medium, and high) that allow developers to tune the depth of internal reasoning before a response is generated. The model accepts text, image, video, audio, and PDF inputs and produces text output, with a 1 million token context window and up to 65,000 output tokens per request. It is natively multimodal, processing visual inputs alongside text to support tasks such as image captioning, classification, optical character recognition, object detection, and visual grounding, where the model references specific regions within an image or video frame.

Its vision capabilities extend to interpreting UI screenshots, diagrams, charts, and real-world scenes, as well as understanding video and live frame sequences for activity and scene recognition. The model supports combined tool use, including Google Search, URL context, code execution, and custom functions, within a single request, and it uses reasoning context from previous turns when thought signatures are present in the conversation history, enabling persistent multi-turn reasoning chains. Gemini 3.5 Flash carries a knowledge cutoff of January 2026 and is available via the Gemini API, Google AI Studio, Google Antigravity, and the Gemini Enterprise Agent Platform.

Gemini 3.5 Flash Interactive Demo

Gemini 3.5 Flash Details & Performance

Details

Resources

—

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRObject DetectionVision LanguageVisual Question Answering

Features

Foundation VisionLLMs with Vision CapabilitiesMultimodal Vision

Usage

Past 30 Days

Performance

Avg. Latency

Arena Rankings

Gemini 3.5 Flash Vision Evals

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

Evals updated August 20, 2026Pricing updated August 23, 2026

Overall score#1 of 31
86.6%
Avg cost / sample#26 of 31
$0.011
Avg speed / sample#7 of 31
5.82s
Avg tokens / sample
2.1K

Strengths and weaknesses

Gemini 3.5 Flash averages 86.6% across the six Vision Evals tasks, ranking #1 of 31 models overall.

It leads the field in Identification and Reasoning.

It also places in the top three for Data Extraction, Object Detection, and Counting.

Its weakest relative showing is OCR, ranking #14 of 31 at 91.1%.

At $0.011 per sample it is the 26th cheapest of the 31 benchmarked models, and its average inference time of 5.8s per sample makes it the 7th fastest.

Performance profile

Field medianGemini 3.5 Flash

Field medians: Object Detection 54.5%, Counting 63.5%, Identification 84.4%, OCR 89.3%, Data Extraction 86.6%, Reasoning 57.6%.

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
68.7%
#3 of 31$0.0168.17s
Counting
81.1%
#3 of 31$0.00753.93s
Identification
100.0%
#1 of 31$0.00422.71s
OCR
91.1%
#14 of 31$0.0167.40s
Data Extraction
94.8%
#2 of 31$0.00372.67s
Reasoning (low)
84.1%
#1 of 31$0.00805.13s
Reasoning (high)
82.8%
#1 of 31$0.0178.78s
  • Thinking longer does not help: 1.3 points lower on reasoning at high effort for 2.2x the cost and 1.7x the latency.

Price vs. performance

Score vs. cost

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

31 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · Gemini 3.5 Flash highlighted

Gemini 3.5 Flash scores from a single evaluation run · Methodology

View all Vision Evals →

Gemini 3.5 Flash Pricing

Gemini 3.5 Flash costs $1.50 per 1M input tokens and $9.00 per 1M output tokens.

Input$1.50 / 1M tokens
Output$9.00 / 1M tokens
Cached input$0.150 / 1M tokens

Pricing updated Aug 23, 2026

Alternatives to Gemini 3.5 Flash

Other models worth comparing for similar use cases.

OpenAI
GPT-5.6 Terra
GPT-5.6 Terra is the mid-tier reasoning model in OpenAI's GPT-5.6 family, which also includes the flagship Sol and the lightweight Luna. Introduced in a limited preview on June 26, 2026, and made broadly available on July 9, 2026, Terra accepts text and image input and produces text output, supporting vision, function calling, tool use, and agentic workflows. It is designed as a balanced option for everyday professional and production workloads — including coding assistance, document analysis, customer support, and multi-step agent tasks — where both output quality and cost efficiency matter. OpenAI positions Terra as delivering performance competitive with GPT-5.5 at approximately half the price, with a context window of around 1,050,000 tokens. On Terminal-Bench 2.1, Terra scores 84.3%, matching Claude Fable 5 on that benchmark. Under OpenAI's Preparedness Framework, Terra is rated High for cybersecurity and biological capabilities, meaning it demonstrates meaningful capability in those domains without reaching the Critical threshold.GPT-5.6 introduces a new naming convention in which the generation number (5.6) is paired with a durable capability tier name (Sol, Terra, or Luna), allowing each tier to advance on its own schedule. Terra carries the API identifier gpt-5.6-terra and supports the same reasoning effort controls available across the family, including adjustable reasoning depth. The model includes prompt caching with explicit cache breakpoints and a 30-minute minimum cache life, with cache writes billed at 1.25x the uncached input rate and cache reads receiving a 90% discount. GPT-5.6 Terra is a proprietary, closed-weights model served through the OpenAI API, Codex, and ChatGPT.
Anthropic
Claude Sonnet 5
Claude Sonnet 5 is a mid-tier large language model from Anthropic, released on June 30, 2026, as the latest model in the Sonnet series and a direct successor to Claude Sonnet 4.6. It is a hybrid reasoning model designed primarily for agentic workflows, software coding, and professional tasks. The model features a 1 million token context window, a 128k maximum output token limit, and runs adaptive thinking by default, giving API users fine-grained control over reasoning effort across five levels (low, medium, high, max, and extra-high). It uses an updated tokenizer shared with Opus 4.7 and later models, which produces approximately 30% more tokens for equivalent text compared to earlier Claude models. On benchmarks, Sonnet 5 scores 63.2% on agentic coding and 81.2% on OSWorld, narrowing the gap with Opus 4.8 while remaining at Sonnet-tier pricing.The model supports text and image input with text output, and accepts tools including browsers and terminals for autonomous multi-step task execution. Anthropic's safety evaluations report that Sonnet 5 shows a lower rate of undesirable behaviors than Sonnet 4.6 and is generally safer in agentic contexts, with improved resistance to prompt injection and reduced sycophancy. Cybersecurity safeguards equivalent to those on Opus 4.7 and 4.8 are active, though Anthropic notes the model was not deliberately trained on cybersecurity tasks. The model is proprietary and API-only, with no open weights.
Qwen
Qwen3.7 Flash
Qwen3.7 Flash is the low-latency, cost-oriented tier of Alibaba's Qwen3.7 series, a vision-language reasoning model that accepts interleaved text and image input and returns text. It is built as a hybrid thinking model: like the rest of the Qwen3.7, Qwen3.6, and Qwen3.5 families served through Alibaba Cloud Model Studio, it can either emit an explicit reasoning trace before answering or respond directly, with thinking behavior controlled by an enable_thinking switch that defaults to on for the Qwen3.7 generation. The model exposes a context window of roughly one million tokens and a maximum generation length of 65,536 tokens, which allows long multi-image sequences, long documents, and extended agent trajectories to be held in a single request.Functionally, Qwen3.7 Flash targets multimodal agent workloads rather than pure chat. Reported strengths include object recognition, spatial understanding, and perception of real-world scenes, alongside visual coding, search, and computer-use style interaction where the model reads screen content and reasons over interface state. Weights are not published; the model is a proprietary endpoint positioned below Qwen3.7 Plus and Qwen3.7 Max in the same series, and it supports function calling and tool use for agentic pipelines.
Qwen
Qwen3.6 35B A3B
Qwen3.6-35B-A3B is a sparse Mixture-of-Experts (MoE) multimodal language model developed by the Qwen team at Alibaba Group. It carries 35 billion total parameters but activates only approximately 3 billion per forward pass via a learned routing mechanism, giving it the representational capacity of a large dense model at a fraction of the inference compute. The model is natively multimodal, processing images, documents, and video alongside text as a core architectural capability rather than an add-on. It supports a native context window of 262,144 tokens, extensible up to 1,010,000 tokens via YaRN. A key design feature is the unified thinking/non-thinking mode framework: users can switch between deliberate chain-of-thought reasoning and fast direct responses within a single model, and a "thinking preservation" option retains reasoning context across multi-turn agentic workflows to reduce redundant computation.The model is specifically optimized for agentic coding tasks, including repository-level reasoning, frontend workflow generation, multi-step tool use, and MCP (Model Context Protocol) integration. On SWE-bench Verified it scores 73.4%, on Terminal-Bench 2.0 it scores 51.5%, and on MCPMark it scores 37.0%. For vision-language tasks it achieves 92.0 on RefCOCO, 89.9 on OmniDocBench 1.5, and 83.7 on VideoMMMU. The model also supports Multi-Token Prediction (MTP) for speculative decoding. All Qwen3.6 open-weight models are released under the Apache 2.0 license.

Other Google Gemini Flash models

Other versions in the same family as Gemini 3.5 Flash.

GoogleGemini 3.7 FlashGoogleGemini 3.6 FlashGoogleGemini 3 FlashGoogleGemini 2.5 Flash

Deploy Gemini 3.5 Flash with an API

Gemini 3.5 Flash 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" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/gemini-3-5-flash-open-prompt
- 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 }, `prompt`: text } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.

With the Roboflow MCP connected, call `workflows_get` on "gemini-3-5-flash-open-prompt" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). 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
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.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 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-open-prompt",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  parameters={
    "prompt": "Describe what you see in the image"
  },
  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.

// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/gemini-3-5-flash-open-prompt', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    api_key: 'YOUR_API_KEY',
    inputs: {
      "image": {"type": "url", "value": "IMAGE_URL"},
      "prompt": "Describe what you see in the image"
    }
  })
});

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

Deploy this workflow to your Roboflow workspace to use it.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/gemini-3-5-flash-open-prompt' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"},
    "prompt": "Describe what you see in the image"
  }
}'

Gemini 3.5 Flash License

Proprietary

Gemini 3.5 Flash is proprietary: the weights are not distributed, and the Gemini 3.5 Flash 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 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?

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 a model whose commercial license is included in your plan — on Roboflow Managed Cloud or a Self-Hosted Inference Server — Roboflow's licensing page lists the supported alternatives to Gemini 3.5 Flash.

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 Vision

Yes. Gemini 3.5 Flash accepts image input and handles OCR, data extraction, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Identification at 100% (#1 of 31). You can test it on your own image in the demo above.

Yes. its transcriptions match the ground truth 91.1% on average (#14 of 31) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 94.9%.

Yes. On Vision Evals, Gemini 3.5 Flash scores 68.7% mAP@50 on object detection (#3 of 31) and 81.1% exact-match accuracy on object counting.

On our benchmark's task mix, Gemini 3.5 Flash averages $0.01 per sample at $1.50 per 1M input and $9.00 per 1M output tokens (#26 of 31 on cost), with an average speed of 5.8s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Gemini 3.5 Flash sits #1 of 31 at 86.6%, just ahead of Gemini 3.7 Flash (84.6%). See the full side-by-side: Gemini 3.5 Flash vs Gemini 3.7 Flash.