Roboflow

AnthropicAnthropicReleased Jun 2026Proprietary

Claude Sonnet 5

Claude Sonnet 5 scores 55.3% overall on Roboflow's Vision Evals (November 16, 2026 snapshot), #54 of 70 models (Claude Sonnet 5.5 ranks higher at 77.6%).

Its weakest task is object detection (36.1%, #58 of 70). It is a proprietary model from Anthropic, so commercial use follows Anthropic's terms.

Vision Evals55.3%Field median 64.8% · #54 of 70
Cost$0.0074/ sampleField median $0.0036 · #47 of 70
Speed5.9s/ sampleField median 10.3s · #8 of 70

Claude Sonnet 5 Interactive Demo

Model settings

Extended thinking

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 Claude Sonnet 5.

Claude Sonnet 5 Vision Evals

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

Evals updated November 16, 2026Pricing updated November 17, 2026

Strengths and weaknesses

Best showing

TaskScoreMedianRank
Counting56.8%65.8%#44 of 70

Weak spot

TaskScoreMedianRank
Object Detection36.1%57.1%#58 of 70

Below the field median.

Score by taskScoreRank
OCR
59.4%#38
Counting
56.8%#44
Reasoning
43.0%#50
Identification
81.3%#52
Object Detection
36.1%#58

Claude Sonnet 5Field median

Ranks out of 70 models (54 for OCR)

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
36.1%
#58 of 70$0.0117.19s
Counting
56.8%
#44 of 70$0.00302.99s
Identification
81.3%
#52 of 70$0.00272.33s
OCR (low)
59.4%
#38 of 54$0.00786.54s
OCR (high)
59.5%
#42 of 54$0.01513.98s
Reasoning (low)
43.0%
#50 of 70$0.00323.09s
Reasoning (high)
43.0%
#56 of 57$0.00434.12s
  • Thinking longer helps: 0.1 points higher on ocr at high effort for 1.9x the cost and 2.1x the latency.
  • Thinking longer changes nothing: the same reasoning score at high effort for 1.4x the cost and 1.3x the latency.

Price vs. performance

Score vs. cost

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

69 of 70 models plotted (the rest have no measured figure for this axis) · scores and efficiency pooled across all five tasks at low effort · Claude Sonnet 5 highlighted

Claude Sonnet 5 scores are from a single run per task; a three-run re-run under the current protocol is pending · Methodology

View all Vision Evals →

Claude Sonnet 5 Overview

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.

Claude Sonnet 5 Pricing

Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens.

Input$2.00 / 1M tokens
Output$10.00 / 1M tokens
Cached input$0.200 / 1M tokens

Pricing updated Nov 17, 2026

Deploy Claude Sonnet 5 with an API

Claude Sonnet 5 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 "Claude Sonnet 5" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/claude-sonnet-5-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 "claude-sonnet-5-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.
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="claude-sonnet-5-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/claude-sonnet-5-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/claude-sonnet-5-object-detection' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"},
    "classes": ["class1", "class2", "class3"]
  }
}'

Claude Sonnet 5 License

Proprietary

Claude Sonnet 5 is proprietary: the weights are not distributed, and the Claude Sonnet 5 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. Claude Sonnet 5 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 Claude Sonnet 5?

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 an open model instead of Claude Sonnet 5, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.

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

License information is provided as a guide and is not legal advice.

Claude Sonnet 5 Details

Details

Categoryclosed
ModalityMultimodal
Context Window1.0M
LicenseProprietary
Release DateJun 2026

Vision Tasks

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

Resources

Usage

Past 30 Days

Alternatives to Claude Sonnet 5

Other models worth comparing for similar use cases.

Gemini 3.6 Flash is a multimodal language model from Google DeepMind, positioned as the workhorse tier in the Gemini 3.x family.
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.
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.
GLM-5.3-Flash is the first natively multimodal model in Z.ai's GLM-5 series, a mixture-of-experts transformer with roughly 320 billion total parameters and 18 billion activated…
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…

Other Anthropic Sonnet models

Other versions in the same family as Claude Sonnet 5.

Frequently Asked Questions About Claude Sonnet 5 Vision

Yes. Claude Sonnet 5 accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is OCR at 59.4% (#38 of 54 at low effort). You can test it on your own image in the demo above.

Yes. it scores 59.4% (#38 of 54 at low effort) on Vision Evals OCR, which covers single readings, full transcriptions, structured JSON, and locating text with boxes. Within that, full transcriptions score 88.6%, and returning the fields of a label or form as JSON scores 78.4%.

Not its strength. On Vision Evals, Claude Sonnet 5 scores 36.1% mAP@50 on object detection (#58 of 70 at low effort) and 56.8% judge-graded 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, Claude Sonnet 5 averages $0.0074 per sample at $2.00 per 1M input and $10.00 per 1M output tokens (#47 of 70 on cost), with an average speed of 5.9s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Claude Sonnet 5 sits #54 of 70 at 55.3%, just behind Grok 4.5 (55.3%) and just ahead of Qwen3 VL 235B A22B Instruct (55.2%). See the full side-by-side: Claude Sonnet 5 vs Grok 4.5.