Gemini 3.7 Flash is a proprietary multimodal model from Google, positioned in the Flash branch of the Gemini 3 series that trades some of the capacity of the larger Pro models for lower latency and lower cost per token. It accepts interleaved text and image input alongside other modalities handled by the Gemini family and returns text, and it continues the series pattern of exposing a configurable thinking budget so that reasoning effort can be scaled up for harder problems or reduced for high throughput extraction, routing and classification work. The model is announced roughly three weeks after Gemini 3.6 Flash, part of an unusually fast iteration cadence within the Flash line.
Google reports gains concentrated in agentic coding and front end generation, citing a WebDev Arena Elo of 1588 for this release compared with 1538 for the preceding Flash model, and describes it as producing more functional layouts and more feature complete applications in fewer prompts. Weights are not published and the architecture, parameter count and training corpus are undisclosed, consistent with prior Gemini releases. Visual capability follows the Flash lineage, covering image and document understanding, chart and diagram interpretation, text recognition in images, and general visual question answering.
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 15, 2026
Gemini 3.7 Flash averages 84.6% across the six Vision Evals tasks, ranking #2 of 30 models overall.
It places in the top three for Object Detection, Data Extraction, and Reasoning.
Its weakest relative showing is OCR, ranking #26 of 30 at 86.9%.
At $0.0016 per sample it is the 8th cheapest of the 30 benchmarked models, and its average inference time of 10.0s per sample makes it the 24th 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 | 69.4% | #2 of 30 | $0.0024 | 8.68s | |
| Counting | 77.0% | #4 of 30 | $0.0013 | 11.77s | |
| Identification | 96.9% | #4 of 30 | $0.0007 | 18.17s | |
| OCR | 86.9% | #26 of 30 | $0.0014 | 16.72s | |
| Data Extraction | 94.8% | #2 of 30 | $0.0007 | 8.73s | |
| Reasoning (low) | 82.8% | #2 of 30 | $0.0011 | 8.62s | |
| Reasoning (high) | 82.1% | #2 of 30 | $0.0026 | 9.24s |
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 3.7 Flash highlighted
Gemini 3.7 Flash scores from a single evaluation run · Methodology
View all Vision Evals →Gemini 3.7 Flash costs $0.375 per 1M input tokens and $1.88 per 1M output tokens.
Pricing updated Aug 15, 2026
Other versions in the same family as Gemini 3.7 Flash.
Gemini 3.7 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. Forking 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).
Fork this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Gemini 3.7 Flash" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-gemini-3-7-flash-c
- 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 "playground-gemini-3-7-flash-c" to read the exact input schema and treat it as the source of truth. A live `workflows_run` for this workflow also needs my OpenRouter 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
- `OPENROUTER_API_KEY` (sent as `model_api_key`) from https://openrouter.ai/keys — my OpenRouter 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-sdkFork 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="playground-gemini-3-7-flash-c",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"model_api_key": "YOUR_OPENROUTER_API_KEY"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Fork this workflow to your Roboflow workspace to use it.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-c', {
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_OPENROUTER_API_KEY"
}
})
});
const result = await response.json();
console.log(result);Fork this workflow to your Roboflow workspace to use it.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-c' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"model_api_key": "YOUR_OPENROUTER_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).
Fork this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Gemini 3.7 Flash" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-gemini-3-7-flash-op
- 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 "playground-gemini-3-7-flash-op" to read the exact input schema and treat it as the source of truth. A live `workflows_run` for this workflow also needs my OpenRouter 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
- `OPENROUTER_API_KEY` (sent as `model_api_key`) from https://openrouter.ai/keys — my OpenRouter 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-sdkFork 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="playground-gemini-3-7-flash-op",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"prompt": "Describe what you see in the image",
"model_api_key": "YOUR_OPENROUTER_API_KEY"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Fork this workflow to your Roboflow workspace to use it.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-op', {
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_OPENROUTER_API_KEY"
}
})
});
const result = await response.json();
console.log(result);Fork this workflow to your Roboflow workspace to use it.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-op' \
--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_OPENROUTER_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).
Fork this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Gemini 3.7 Flash" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-gemini-3-7-flash-mlc
- 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 "playground-gemini-3-7-flash-mlc" to read the exact input schema and treat it as the source of truth. A live `workflows_run` for this workflow also needs my OpenRouter 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
- `OPENROUTER_API_KEY` (sent as `model_api_key`) from https://openrouter.ai/keys — my OpenRouter 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-sdkFork 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="playground-gemini-3-7-flash-mlc",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"],
"model_api_key": "YOUR_OPENROUTER_API_KEY"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Fork this workflow to your Roboflow workspace to use it.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-mlc', {
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_OPENROUTER_API_KEY"
}
})
});
const result = await response.json();
console.log(result);Fork this workflow to your Roboflow workspace to use it.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-mlc' \
--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_OPENROUTER_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).
Fork this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Gemini 3.7 Flash" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-gemini-3-7-flash-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 "playground-gemini-3-7-flash-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 OpenRouter 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
- `OPENROUTER_API_KEY` (sent as `model_api_key`) from https://openrouter.ai/keys — my OpenRouter 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-sdkFork 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="playground-gemini-3-7-flash-ocr",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"model_api_key": "YOUR_OPENROUTER_API_KEY"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Fork this workflow to your Roboflow workspace to use it.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-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_OPENROUTER_API_KEY"
}
})
});
const result = await response.json();
console.log(result);Fork this workflow to your Roboflow workspace to use it.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/playground-gemini-3-7-flash-ocr' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"model_api_key": "YOUR_OPENROUTER_API_KEY"
}
}'Gemini 3.7 Flash is proprietary: the weights are not distributed, and the Gemini 3.7 Flash 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 3.7 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 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 3.7 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 Object Detection at 69.4% (#2 of 30). You can test it on your own image in the demo above.
Yes. its transcriptions match the ground truth 86.9% on average (#26 of 30) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 94.9%.
Yes. On Vision Evals, Gemini 3.7 Flash scores 69.4% mAP@50 on object detection (#2 of 30) and 77% exact-match accuracy on object counting.
On our benchmark's task mix, Gemini 3.7 Flash averages $0.0016 per sample at $0.38 per 1M input and $1.88 per 1M output tokens (#8 of 30 on cost), with an average speed of 10.0s per sample across the benchmark. Actual cost depends on your images and prompts.
On the overall Vision Evals ranking, Gemini 3.7 Flash sits #2 of 30 at 84.6%, just behind Gemini 3.5 Flash (86.6%) and just ahead of Qwen3.8-Max (84%). See the full side-by-side: Gemini 3.7 Flash vs Gemini 3.5 Flash.