Gemini 3.8 Flash is a natively multimodal reasoning model in Google's Gemini 3 series, positioned as the speed and cost oriented Flash tier while targeting long-horizon software engineering, autonomous agents, and enterprise workflows. It accepts text, images, video, audio, and PDF documents in a single request and returns text, with an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Thinking is configurable at low, medium, and high levels, and the model supports function calling, code execution, structured outputs, context caching, search and Maps grounding, file search, and computer use in preview. Image generation, audio generation, and the Live API are not supported.
On vision oriented evaluations the model reports 86.2% on CharXiv Reasoning for chart and figure synthesis and 87.8% on LVBench for long video understanding in agentic mode, alongside 90.8% on Terminal-Bench 2.1 and 61.6% on SWE-Bench Pro for coding. Following Gemini API conventions, it can localize objects by emitting bounding boxes as [ymin, xmin, ymax, xmax] integers normalized to a 0 to 1000 range, which supports prompt driven detection and grounding in addition to captioning, document parsing, and visual question answering. The knowledge cutoff is March 2026, though coverage in some domains reflects the January 2025 cutoff shared across the Gemini 3 family.
Drag and drop an image here, or click to browse
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 3.8 Flash.
—
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 September 2, 2026Pricing updated September 2, 2026
Gemini 3.8 Flash averages 85.1% across the six Vision Evals tasks, ranking #3 of 36 models overall.
It leads the field in Data Extraction.
It also places in the top three for Reasoning.
Its weakest relative showing is OCR, ranking #30 of 36 at 87.3%.
At $0.0033 per sample it is the 19th cheapest of the 36 benchmarked models, and its average inference time of 11.6s per sample makes it the 28th fastest.
Field medians: Object Detection 55.5%, Counting 62.2%, Identification 85.9%, OCR 89.1%, Data Extraction 86.6%, Reasoning 56.6%.
| Task | Score | Field (0 to 100) | Rank | Cost / sample | Speed |
|---|---|---|---|---|---|
| Object Detection (low) | 68.1% ±0.8, Mean of 3 runs, range 67.3 to 69.0 | #5 of 36 | $0.0041 | 17.01s | |
| Object Detection (high) | 74.8% ±1.1, Mean of 3 runs, range 73.4 to 75.6 | #1 of 5 | $0.021 | 20.96s | |
| Counting (low) | 78.8% ±2.7, Mean of 3 runs, range 75.7 to 81.1 | #4 of 36 | $0.0036 | 9.67s | |
| Counting (high) | 79.3% ±1.4, Mean of 3 runs, range 78.4 to 81.1 | #2 of 5 | $0.024 | 25.19s | |
| Identification (low) | 97.9% ±1.6, Mean of 3 runs, range 96.9 to 100.0 | #5 of 36 | $0.0014 | 7.44s | |
| Identification (high) | 96.9% ±0.0, Mean of 3 runs, range 96.9 to 96.9 | #3 of 5 | $0.0034 | 8.12s | |
| OCR (low) | 87.3% ±0.8, Mean of 3 runs, range 86.5 to 88.2 | #30 of 36 | $0.0024 | 5.58s | |
| OCR (high) | 88.8% ±0.7, Mean of 3 runs, range 88.0 to 89.4 | #5 of 5 | $0.064 | 57.30s | |
| Data Extraction (low) | 97.3% ±0.5, Mean of 3 runs, range 96.9 to 97.9 | #1 of 36 | $0.0018 | 7.21s | |
| Data Extraction (high) | 94.8% ±1.0, Mean of 3 runs, range 93.8 to 95.9 | #3 of 5 | $0.0089 | 12.87s | |
| Reasoning (low) | 81.2% ±0.3, Mean of 3 runs, range 80.8 to 81.5 | #2 of 36 | $0.0034 | 8.98s | |
| Reasoning (high) | 84.5% ±1.0, Mean of 3 runs, range 83.4 to 85.4 | #1 of 36 | $0.021 | 21.81s |
Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.
36 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · Gemini 3.8 Flash highlighted
Gemini 3.8 Flash scores are the mean of 3 runs per task at both low and high effort · Methodology
View all Vision Evals →Other versions in the same family as Gemini 3.8 Flash.
Gemini 3.8 Flash is proprietary: the weights are not distributed, and the Gemini 3.8 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 3.8 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 3.8 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 Data Extraction at 97.3% (#1 of 36 at low effort). You can test it on your own image in the demo above.
Yes. its transcriptions match the ground truth 87.4% on average (#30 of 36 at low effort) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 97.3%.
Yes. On Vision Evals, Gemini 3.8 Flash scores 68.1% mAP@50 on object detection (#5 of 36 at low effort) and 78.8% judge-graded accuracy on object counting.
On our benchmark's task mix, Gemini 3.8 Flash averages $0.0033 per sample (#19 of 36 on cost), with an average speed of 11.6s per sample across the benchmark. Actual cost depends on your images and prompts.
On the overall Vision Evals ranking, Gemini 3.8 Flash sits #3 of 36 at 85.1%, just behind Gemini 3.7 Flash (85.2%) and just ahead of Qwen3.8 Max (84%). See the full side-by-side: Gemini 3.8 Flash vs Gemini 3.7 Flash.