Claude Opus 4.6 is the flagship large language model from Anthropic, released on 2026-02-05 for advanced reasoning, complex coding, and enterprise agent workflows. It supports text and image inputs via API, offers a 200K-token standard context window with a 1M-token beta option, and enables outputs up to 128K tokens, with adaptive reasoning and context compaction for sustained tasks.
As of 2026-02-17, Anthropic also released Claude Sonnet 4.6, extending the 1M-token context window to a broader tier. Opus remains positioned for maximum depth and benchmark performance, while Sonnet 4.6 brings long-context capability to more cost- and latency-sensitive production use cases.
Drag and drop an image here, or click to browse
—
Usage
Past 30 DaysClaude Opus 4.6 has not yet been evaluated on the current benchmark. The results below are from the legacy version of Vision Evals, our previous benchmark. See the current Vision Evals
| Category | Passed | Score |
|---|---|---|
| Document Understanding | 7 / 9 | 77.8% |
| Defect Detection | 11 / 15 | 73.3% |
| Object Understanding | 10 / 14 | 71.4% |
| Spatial Understanding | 13 / 19 | 68.4% |
| Object Counting | 2 / 10 | 20% |
| Category | Passed | Score |
|---|---|---|
| License Plate Recognition | 27 / 30 | 90% |
| Focused Scene OCR | 85 / 99 | 85.9% |
| Text Recognition | 24 / 30 | 80% |
| VQA & Extraction | 46 / 60 | 76.7% |
| Handwritten Math | 7 / 10 | 70% |
Scores based on a single evaluation run · Methodology
View all legacy Vision Evals results →Claude Opus 4.6 costs $5.00 per 1M input tokens and $25.00 per 1M output tokens.
Pricing updated Aug 5, 2026
Estimated cost per task vs. Visual Understanding score, for this model and others ranked near it. Upper-left is the sweet spot (high quality, low cost). Based on Vision Evals (legacy) results.
11 of 11 models plotted
| Model | Score | Median tokens | Est. cost / task | Compare |
|---|---|---|---|---|
| Gemma 4 26B A4B | 68.7% | 531 | $0.0001 | Compare |
| Qwen3.6 Plus | 68.7% | 1.6K | $0.0005 | Compare |
| Claude Opus 4.8 | 67.2% | 2.2K | $0.012 | Compare |
| Claude Opus 4.7 | 67.2% | 2.6K | $0.015 | Compare |
| Gemma 4 31B | 67.2% | 467 | $0.0001 | Compare |
| Claude Opus 4.6 (this model) | 64.2% | 2.3K | $0.014 | — |
| GPT-5.4 Nano | 62.7% | 1.8K | $0.0004 | Compare |
| Llama 4 Maverick | 59.7% | 2.4K | $0.0005 | Compare |
| Claude Sonnet 4.5 | 59.7% | 2.3K | $0.0092 | Compare |
| Claude Opus 4.1 | 59.7% | 2.1K | $0.040 | Compare |
| Claude Haiku 4.5 | 58.2% | 2.3K | $0.0030 | Compare |
Other models worth comparing for similar use cases.
Other versions in the same family as Claude Opus 4.6 .
Claude Opus 4.6 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 "Claude Opus 4.6 " workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-claude-4-6-opus-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-claude-4-6-opus-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 Anthropic 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
- `ANTHROPIC_API_KEY` (sent as `model_api_key`) from https://console.anthropic.com/settings/keys — my Anthropic 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-claude-4-6-opus-op",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"prompt": "Describe what you see in the image",
"model_api_key": "YOUR_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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 "Claude Opus 4.6 " workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-claude-4-6-opus-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-claude-4-6-opus-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 Anthropic 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
- `ANTHROPIC_API_KEY` (sent as `model_api_key`) from https://console.anthropic.com/settings/keys — my Anthropic 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-claude-4-6-opus-ocr",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"model_api_key": "YOUR_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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-claude-4-6-opus-ocr' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"model_api_key": "YOUR_ANTHROPIC_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 "Claude Opus 4.6 " workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-claude-4-6-opus-od
- 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-claude-4-6-opus-od" to read the exact input schema and treat it as the source of truth. A live `workflows_run` for this workflow also needs my Anthropic 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
- `ANTHROPIC_API_KEY` (sent as `model_api_key`) from https://console.anthropic.com/settings/keys — my Anthropic 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-claude-4-6-opus-od",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"],
"model_api_key": "YOUR_ANTHROPIC_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-claude-4-6-opus-od', {
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_ANTHROPIC_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-claude-4-6-opus-od' \
--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_ANTHROPIC_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 "Claude Opus 4.6 " workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-claude-4-6-opus-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-claude-4-6-opus-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 Anthropic 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
- `ANTHROPIC_API_KEY` (sent as `model_api_key`) from https://console.anthropic.com/settings/keys — my Anthropic 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-claude-4-6-opus-mlc",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"],
"model_api_key": "YOUR_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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 "Claude Opus 4.6 " workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/playground-claude-4-6-opus-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-claude-4-6-opus-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 Anthropic 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
- `ANTHROPIC_API_KEY` (sent as `model_api_key`) from https://console.anthropic.com/settings/keys — my Anthropic 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-claude-4-6-opus-c",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"model_api_key": "YOUR_ANTHROPIC_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-claude-4-6-opus-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_ANTHROPIC_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-claude-4-6-opus-c' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"model_api_key": "YOUR_ANTHROPIC_API_KEY"
}
}'License terms and commercial-use guidance for Claude Opus 4.6 .
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.
Yes. Claude Opus 4.6 accepts image input, and on Roboflow's previous vision benchmark it passed 64.2% of visual understanding tasks (#36 of 77) and scored 82.5% on OCR. You can test it on your own image in the demo above.
Claude Opus 4.6 has not yet been evaluated on Roboflow's current Vision Evals. The results on this page are from the previous benchmark.
Yes. The demo on this page runs Claude Opus 4.6 in the free Roboflow Playground: upload an image and see results in seconds. A free account unlocks unlimited runs.