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.
Drag and drop an image here, or click to browse
Captioning will run automatically
—
Usage
Past 30 DaysVision 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 14, 2026Pricing updated August 18, 2026
Gemini 3.5 Flash-Lite averages 69.6% across the six Vision Evals tasks, ranking #16 of 30 models overall.
Its weakest relative showing is OCR, ranking #25 of 30 at 87.4%.
At $0.0014 per sample it is the 7th cheapest of the 30 benchmarked models, and its average inference time of 2.7s per sample makes it the fastest.
Field medians: Object Detection 55.2%, Counting 64.2%, Identification 84.4%, OCR 90.0%, Data Extraction 86.6%, Reasoning 58.0%.
| Task | Score | Field (0 to 100) | Rank | Cost / sample | Speed |
|---|---|---|---|---|---|
| Object Detection | 57.5% | #12 of 30 | $0.0023 | 4.09s | |
| Counting | 52.7% | #21 of 30 | $0.0007 | 1.68s | |
| Identification | 81.3% | #17 of 30 | $0.0004 | 1.23s | |
| OCR | 87.4% | #25 of 30 | $0.0011 | 1.57s | |
| Data Extraction | 90.7% | #7 of 30 | $0.0004 | 1.33s | |
| Reasoning (low) | 48.3% | #20 of 30 | $0.0012 | 2.38s | |
| Reasoning (high) | 68.9% | #13 of 30 | $0.0042 | 5.82s |
Overall benchmark score against estimated cost per sample. Upper-left is the sweet spot: high quality at low cost.
30 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · Gemini 3.5 Flash-Lite highlighted
Gemini 3.5 Flash-Lite scores from a single evaluation run · Methodology
View all Vision Evals →Gemini 3.5 Flash-Lite costs $0.300 per 1M input tokens and $2.50 per 1M output tokens.
Pricing updated Aug 18, 2026
Other models worth comparing for similar use cases.
Other versions in the same family as Gemini 3.5 Flash-Lite.
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.
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.pip install inference-sdkDeploy 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"
}
}'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-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, `model_api_key`: my provider key } }.
With the Roboflow MCP connected, call `workflows_get` on "gemini-3-5-flash-lite-open-prompt" 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.pip install inference-sdkDeploy 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-open-prompt",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"prompt": "Describe what you see in the image",
"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-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",
"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-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",
"model_api_key": "YOUR_GOOGLE_API_KEY"
}
}'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-classification
- 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 }, `classes`: string array, `model_api_key`: my provider key } }.
With the Roboflow MCP connected, call `workflows_get` on "gemini-3-5-flash-lite-classification" 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.pip install inference-sdkDeploy 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-classification",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"],
"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-classification', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"],
"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-classification' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"],
"model_api_key": "YOUR_GOOGLE_API_KEY"
}
}'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-object-detection
- 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 }, `classes`: string array } }.
- 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-lite-object-detection" 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.pip install inference-sdkDeploy 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-lite-object-detection",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"]
},
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-lite-object-detection', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
})
});
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-lite-object-detection' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
}'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-ocr
- 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-ocr" 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.pip install inference-sdkDeploy 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-ocr",
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-ocr', {
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-ocr' \
--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 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.
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.
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-Lite.
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 salesThis 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.
Yes. Gemini 3.5 Flash-Lite 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 Data Extraction at 90.7% (#7 of 30). You can test it on your own image in the demo above.
Yes. its transcriptions match the ground truth 87.4% on average (#25 of 30) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 90.7%.
Not its strength. On Vision Evals, Gemini 3.5 Flash-Lite scores 57.5% mAP@50 on object detection (#12 of 30) and 52.7% exact-match 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 (#7 of 30 on cost), with an average speed of 2.7s 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 #16 of 30 at 69.6%, just behind Muse Glimmer 30B (70.8%) and just ahead of Grok 4.6 (67.8%). See the full side-by-side: Gemini 3.5 Flash-Lite vs Muse Glimmer 30B.