Using Claude Opus 4.5 in your workflow
Sorceress brings Anthropic models into a shared API catalog. Select this model explicitly, check its supported inputs, and keep your API key on your server. Model capabilities differ; the schema and options on this page describe this entry rather than every model from the same brand.
- Draft, explain and refine content in a conversation.
- Use a consistent chat endpoint while choosing a model suited to your task.
Pricing and availability
Sorceress pricing is awaiting activation. The reference catalog lists 285 credits / M input tokens, 1430 / M output; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.
Inputs and supported options
{
"type": "object",
"required": [
"model",
"messages"
],
"properties": {
"model": {
"type": "string",
"title": "Model",
"enum": [
"claude-opus-4-5"
],
"default": "claude-opus-4-5"
},
"messages": {
"type": "array",
"title": "Messages",
"description": "The conversation so far, oldest first. Content is a string or text / image_url parts. Video files use image_url only on models whose chat_capabilities.video_input is true.",
"minItems": 1,
"items": {
"type": "object",
"required": [
"role"
],
"properties": {
"role": {
"type": "string",
"title": "Role",
"enum": [
"system",
"developer",
"user",
"assistant",
"tool"
]
},
"content": {
"title": "Content",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"text",
"image_url"
]
},
"text": {
"type": "string"
},
"image_url": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri"
},
"detail": {
"type": "string",
"enum": [
"auto",
"low",
"high"
]
},
"mime_type": {
"type": "string",
"description": "Optional image or video MIME type for a hosted reference."
}
}
}
}
}
}
]
},
"name": {
"type": "string",
"title": "Name"
},
"tool_calls": {
"type": "array",
"title": "Tool calls",
"items": {
"type": "object"
}
},
"tool_call_id": {
"type": "string",
"title": "Tool call ID"
}
}
}
},
"tools": {
"type": "array",
"title": "Tools",
"description": "Function tools the model may call: { type: \"function\", function: { name, description, parameters } }.",
"items": {
"type": "object"
}
},
"tool_choice": {
"title": "Tool choice",
"description": "\"auto\", \"none\", \"required\" or { type: \"function\", function: { name } }.",
"oneOf": [
{
"type": "string",
"enum": [
"auto",
"none",
"required"
]
},
{
"type": "object"
}
]
},
"stream": {
"type": "boolean",
"title": "Stream",
"description": "Server-sent events; the final chunk carries usage and the credits charged.",
"default": false
},
"max_tokens": {
"type": "integer",
"title": "Max tokens",
"description": "Upper bound on the number of tokens generated for the reply (reasoning tokens included).",
"minimum": 1,
"maximum": 128000,
"default": 4096
},
"temperature": {
"type": "number",
"title": "Temperature",
"minimum": 0,
"maximum": 2
},
"top_p": {
"type": "number",
"title": "Top p",
"minimum": 0,
"maximum": 1
},
"stop": {
"title": "Stop",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 4
}
]
},
"response_format": {
"type": "object",
"title": "Response format",
"description": "{ type: \"text\" | \"json_object\" }",
"properties": {
"type": {
"type": "string",
"enum": [
"text",
"json_object"
]
}
}
},
"reasoning_effort": {
"type": "string",
"title": "Reasoning",
"enum": [
"none",
"enabled"
],
"description": "Choose a supported reasoning setting. Omit to use the model default."
}
}
}Completion, results and billing
Save the job identifier returned by asynchronous requests and poll the jobs endpoint until the job succeeds or fails. Do not resubmit a generation just because it is still processing. Chat returns a completed reply and usage details. A multi-step workflow can include separately billed successful steps even if a later step fails. Keep returned asset links with your project, and consult each action for its output format.
Coding agents can discover the current catalog and input requirements from the Sorceress agent instructions. Use a Sorceress key; provider credentials stay on the server.