Anthropic Claude¶

v3¶

Class: AnthropicClaudeBlockV3 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v3.AnthropicClaudeBlockV3

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

Open Prompt (unconstrained) - Use any prompt to generate a raw response
Text Recognition (OCR) (ocr) - Model recognizes text in the image
Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt
Captioning (short) (caption) - Model provides a short description of the image
Captioning (detailed-caption) - Model provides a long description of the image
Single-Label Classification (classification) - Model classifies the image content as one of the provided classes
Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes
Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image
Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

API Key Options¶

This block supports two API key modes:

Roboflow Managed API Key (Default) - Use rf_key:account to proxy requests through Roboflow's API:
Simplified setup - no Anthropic API key required
Secure - your workflow API key is used for authentication
Usage-based billing - charged per token based on the model used
Custom Anthropic API Key - Provide your own Anthropic API key:
Full control over API usage
You pay Anthropic directly

Type identifier¶

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v3to add the block as as step in your workflow.

Properties¶

Name	Type	Description	Refs
`name`	`str`	Enter a unique identifier for this step..	❌
`task_type`	`str`	Task type to be performed by model. Value determines required parameters and output response..	❌
`prompt`	`str`	Text prompt to the Claude model.	✅
`output_structure`	`Dict[str, str]`	Dictionary with structure of expected JSON response.	❌
`classes`	`List[str]`	List of classes to be used.	✅
`api_key`	`str`	Your Anthropic API key or 'rf_key:account' to use Roboflow's managed API key.	✅
`model_version`	`str`	Model to be used.	✅
`extended_thinking`	`bool`	Enable extended thinking for deeper reasoning on complex tasks. Note: temperature cannot be used when extended thinking is enabled..	❌
`thinking_budget_tokens`	`int`	Maximum number of tokens for internal thinking when extended thinking is enabled. Higher values allow deeper reasoning but increase latency and cost. Must be less than max_tokens. Minimum: 1024..	❌
`max_tokens`	`int`	Maximum number of tokens the model can generate in its response..	❌
`temperature`	`float`	Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..	✅
`max_image_size`	`int`	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
`max_concurrent_requests`	`int`	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Runtime compatibility¶

requires_internet — air-gapped / offline deployments: This block depends on a service that is not reachable from fully offline / air-gapped deployments.

Available Connections¶

Compatible Blocks

Check what blocks you can connect to Anthropic Claude in version v3.

Input and Output Bindings¶

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v3 has.

Bindings

input
- images (image): The image to infer on..
- prompt (string): Text prompt to the Claude model.
- classes (list_of_values): List of classes to be used.
- api_key (Union[secret, string, ROBOFLOW_MANAGED_KEY]): Your Anthropic API key or 'rf_key:account' to use Roboflow's managed API key.
- model_version (string): Model to be used.
- temperature (float): Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..
- max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.
output
- output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
- classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v3

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v3",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "rf_key:account",
    "model_version": "claude-sonnet-4-5",
    "extended_thinking": "<block_does_not_provide_example>",
    "thinking_budget_tokens": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v2¶

Class: AnthropicClaudeBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v2.AnthropicClaudeBlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

Open Prompt (unconstrained) - Use any prompt to generate a raw response
Text Recognition (OCR) (ocr) - Model recognizes text in the image
Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt
Captioning (short) (caption) - Model provides a short description of the image
Captioning (detailed-caption) - Model provides a long description of the image
Single-Label Classification (classification) - Model classifies the image content as one of the provided classes
Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes
Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image
Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

You need to provide your Anthropic API key to use the Claude model.

Type identifier¶

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v2to add the block as as step in your workflow.

Properties¶

Name	Type	Description	Refs
`name`	`str`	Enter a unique identifier for this step..	❌
`task_type`	`str`	Task type to be performed by model. Value determines required parameters and output response..	❌
`prompt`	`str`	Text prompt to the Claude model.	✅
`output_structure`	`Dict[str, str]`	Dictionary with structure of expected JSON response.	❌
`classes`	`List[str]`	List of classes to be used.	✅
`api_key`	`str`	Your Anthropic API key.	✅
`model_version`	`str`	Model to be used.	✅
`extended_thinking`	`bool`	Enable extended thinking for deeper reasoning on complex tasks. Note: temperature cannot be used when extended thinking is enabled..	❌
`thinking_budget_tokens`	`int`	Maximum number of tokens for internal thinking when extended thinking is enabled. Higher values allow deeper reasoning but increase latency and cost. Must be less than max_tokens. Minimum: 1024..	❌
`max_tokens`	`int`	Maximum number of tokens the model can generate in its response..	❌
`temperature`	`float`	Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..	✅
`max_image_size`	`int`	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
`max_concurrent_requests`	`int`	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Runtime compatibility¶

requires_internet — air-gapped / offline deployments: This block depends on a service that is not reachable from fully offline / air-gapped deployments.

Available Connections¶

Compatible Blocks

Check what blocks you can connect to Anthropic Claude in version v2.

Input and Output Bindings¶

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v2 has.

Bindings

input
- images (image): The image to infer on..
- prompt (string): Text prompt to the Claude model.
- classes (list_of_values): List of classes to be used.
- api_key (Union[secret, string]): Your Anthropic API key.
- model_version (string): Model to be used.
- temperature (float): Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..
- max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.
output
- output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
- classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v2",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "xxx-xxx",
    "model_version": "claude-sonnet-4-5",
    "extended_thinking": "<block_does_not_provide_example>",
    "thinking_budget_tokens": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v1¶

Class: AnthropicClaudeBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v1.AnthropicClaudeBlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

Open Prompt (unconstrained) - Use any prompt to generate a raw response
Text Recognition (OCR) (ocr) - Model recognizes text in the image
Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt
Captioning (short) (caption) - Model provides a short description of the image
Captioning (detailed-caption) - Model provides a long description of the image
Single-Label Classification (classification) - Model classifies the image content as one of the provided classes
Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes
Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image
Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

You need to provide your Anthropic API key to use the Claude model.

Type identifier¶

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v1to add the block as as step in your workflow.

Properties¶

Name	Type	Description	Refs
`name`	`str`	Enter a unique identifier for this step..	❌
`task_type`	`str`	Task type to be performed by model. Value determines required parameters and output response..	❌
`prompt`	`str`	Text prompt to the Claude model.	✅
`output_structure`	`Dict[str, str]`	Dictionary with structure of expected JSON response.	❌
`classes`	`List[str]`	List of classes to be used.	✅
`api_key`	`str`	Your Anthropic API key.	✅
`model_version`	`str`	Model to be used.	✅
`max_tokens`	`int`	Maximum number of tokens the model can generate in it's response..	❌
`temperature`	`float`	Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..	✅
`max_image_size`	`int`	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
`max_concurrent_requests`	`int`	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Runtime compatibility¶

requires_internet — air-gapped / offline deployments: This block depends on a service that is not reachable from fully offline / air-gapped deployments.

Available Connections¶

Compatible Blocks

Check what blocks you can connect to Anthropic Claude in version v1.

Input and Output Bindings¶

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v1 has.

Bindings

input
- images (image): The image to infer on..
- prompt (string): Text prompt to the Claude model.
- classes (list_of_values): List of classes to be used.
- api_key (Union[secret, string]): Your Anthropic API key.
- model_version (string): Model to be used.
- temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..
- max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.
output
- output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
- classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v1",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "xxx-xxx",
    "model_version": "claude-sonnet-4",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}