Roboflow
Qwen

Qwen: Qwen3.7 Flash

Qwen3.7 Flash Overview

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.

Qwen3.7 Flash Interactive Demo

Qwen3.7 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

Qwen3.7 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 6, 2026Pricing updated August 11, 2026

Overall score#24 of 25
61.7%
Avg cost / sample#1 of 25
$0.0001
Avg speed / sample#9 of 25
6.32s
Avg tokens / sample
1.5K

Strengths and weaknesses

Qwen3.7 Flash averages 61.7% across the six Vision Evals tasks, ranking #24 of 25 models overall.

Its weakest relative showing is OCR, ranking #25 of 25 at 84.1%.

At $0.0001 per sample it is the cheapest of the 25 benchmarked models, and its average inference time of 6.3s per sample makes it the 9th fastest.

Performance profile

Field medianQwen3.7 Flash

Field medians: Object Detection 56.0%, Counting 63.5%, Identification 84.4%, OCR 89.3%, Data Extraction 86.6%, Reasoning 55.6%.

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
42.8%
#18 of 25$0.00019.54s
Counting
46.0%
#24 of 25<$0.00013.18s
Identification
84.4%
#12 of 25<$0.00013.54s
OCR
84.1%
#25 of 25$0.000111.39s
Data Extraction
78.3%
#23 of 25<$0.00013.49s
Reasoning (low)
34.4%
#22 of 25<$0.00013.70s
Reasoning (high)
60.9%
#19 of 25$0.000559.29s
  • Thinking longer helps: 26.5 points higher on reasoning at high effort for 15.3x the cost and 16x 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.

25 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · Qwen 3.7 Flash highlighted

Qwen3.7 Flash scores from a single evaluation run · Methodology

View all Vision Evals →

Qwen3.7 Flash Pricing

Qwen3.7 Flash costs $0.030 per 1M input tokens and $0.130 per 1M output tokens.

Input$0.030 / 1M tokens
Output$0.130 / 1M tokens
Cached input$0.006 / 1M tokens

Pricing updated Aug 11, 2026

Alternatives to Qwen3.7 Flash

Other models worth comparing for similar use cases.

Google
Gemini 3.6 Flash
Gemini 3.6 Flash is a multimodal language model from Google DeepMind, positioned as the workhorse tier in the Gemini 3.x family. It accepts text, image, video, audio, and PDF inputs with a 1 million token context window and produces up to 64,000 output tokens. The model builds directly on Gemini 3.5 Flash, incorporating developer and customer feedback to improve token efficiency, coding quality, and knowledge work performance. According to the Artificial Analysis Index, it consumes 17% fewer output tokens than its predecessor, and on some benchmarks such as DeepSWE, token reduction reaches up to 65%. It supports function calling, structured output, search as a tool, and code execution, and includes computer use as a built-in capability in the Gemini API and Gemini Enterprise.On coding benchmarks, Gemini 3.6 Flash scores 49% on DeepSWE versus 37% for 3.5 Flash, and 63.9% on MLE Bench versus 49.7%. Computer use performance on OSWorld-Verified improves from 78.4% to 83%, and knowledge work scores on GDPval-AA v2 rise from 1349 to 1421. The model carries a knowledge cutoff of March 2026 and ships with enhanced Frontier Safety safeguards covering chemical, biological, radiological, nuclear, and cyber offense domains, with training to minimize refusals for beneficial uses. It is a proprietary, closed-weights model available in preview through the Gemini API via Google AI Studio, Android Studio, Google Antigravity, Gemini Enterprise, and the Gemini app.
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
Qwen3.6 Flash
Qwen3.6-Flash is the production API variant of the Qwen3.6 model series, developed by the Qwen team at Alibaba Group. It is built on the Qwen3.6-35B-A3B architecture, which combines a hybrid linear attention mechanism with sparse Mixture-of-Experts (MoE) routing to achieve high-throughput inference with reduced latency. The model is natively multimodal, processing both text and images within a unified early-fusion architecture, and supports 201 languages and dialects. It operates in a hybrid thinking mode, capable of generating explicit chain-of-thought reasoning before producing a final response, with the option to disable thinking for direct output. A Thinking Preservation feature allows reasoning context to be retained across multi-turn conversations, which is particularly useful for iterative agentic workflows.The model is trained with reinforcement learning scaled across large-scale agent environments and covers a broad range of tasks including agentic coding, frontend development, visual understanding, document processing, and tool use. Compared to the open-weight Qwen3.6-35B-A3B, the Flash API variant extends the default context window to 1 million tokens and includes built-in production features such as native function calling and official tool integrations. The underlying architecture achieves near-100% multimodal training efficiency relative to text-only training, and the model demonstrates strong performance on agentic coding benchmarks including SWE-bench Verified.
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.
Google
Gemma 4 31B
Gemma 4 31B is the largest dense model in Google's Gemma 4 family, built from the same research as Gemini 3 and released as open weights under the Apache 2.0 license. It supports a 256K token context window with text and image input, configurable thinking mode for step-by-step reasoning, and multilingual support across 140+ languages. The unquantized model fits on a single 80GB GPU.For vision tasks, Gemma 4 31B supports image understanding with variable aspect ratios and resolutions, and can output structured bounding boxes for UI element detection, making it useful for document parsing and UI understanding. Compared to Gemma 3, it delivers stronger reasoning and multimodal performance. It is part of a four-size family alongside the 26B A4B MoE variant and two on-device models (E2B, E4B), with the 31B dense variant optimized for output quality and fine-tuning over inference speed.

Deploy Qwen3.7 Flash with an API

Qwen3.7 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. 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 "Qwen3.7 Flash" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-7-flash-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 "qwen3-7-flash-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 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.
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="qwen3-7-flash-captioning",
  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)

Deploy this workflow to your Roboflow workspace to use it.

const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-7-flash-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_OPENROUTER_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/qwen3-7-flash-captioning' \
--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"
  }
}'

Qwen3.7 Flash License

Proprietary

Qwen3.7 Flash is proprietary: the weights are not distributed, and the Qwen3.7 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. Qwen3.7 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 Qwen3.7 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 Qwen3.7 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 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 Qwen3.7 Flash Vision

Yes. Qwen3.7 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 Identification at 84.4% (#12 of 25). You can test it on your own image in the demo above.

Yes. its transcriptions match the ground truth 84.1% on average (#25 of 25) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 78.4%.

Not its strength. On Vision Evals, Qwen3.7 Flash scores 42.8% mAP@50 on object detection (#18 of 25) and 46% 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, Qwen3.7 Flash averages $0.0001 per sample at $0.03 per 1M input and $0.13 per 1M output tokens (#1 of 25 on cost), with an average speed of 6.3s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Qwen3.7 Flash sits #24 of 25 at 61.7%, just behind GPT-5.4 mini (63.5%) and just ahead of Kimi K2.6 (59%). See the full side-by-side: Qwen3.7 Flash vs GPT-5.4 mini.