Messages
Count tokens in a Message
ModelsExpand Collapse
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class CacheControlEphemeral: …
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CacheCreation: …
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationsConfigParam: …
class CitationsDelta: …
citation: Citation
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["citations_delta"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
Regular text content.
Regular text content.
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ThinkingBlockParam: …
type: Literal["thinking"]
class RedactedThinkingBlockParam: …
type: Literal["redacted_thinking"]
class ToolUseBlockParam: …
type: Literal["tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolResultBlockParam: …
type: Literal["tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
content: Optional[Union[str, List[Content], null]]
Content = List[Content]
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ServerToolUseBlockParam: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class WebSearchToolResultBlockParam: …
type: Literal["web_search_result"]
class WebSearchToolRequestError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class InputJSONDelta: …
type: Literal["input_json_delta"]
class Message: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
class Tool: …
input_schema: InputSchemaJSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
JSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
type: Literal["object"]
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Description of what this tool does.
Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema.
type: Optional[Literal["custom"]]
class ToolBash20250124: …
name: Literal["bash"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["bash_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250124: …
name: Literal["str_replace_editor"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250429: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250429"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250728: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250728"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.
class WebSearchTool20250305: …
name: Literal["web_search"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["web_search_20250305"]
If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.
If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of times the tool can be used in the API request.
user_location: Optional[UserLocation]Parameters for the user's location. Used to provide more relevant search results.
Parameters for the user's location. Used to provide more relevant search results.
type: Literal["approximate"]
The city of the user.
The region of the user.
class MessageDeltaUsage: …
The cumulative number of input tokens used to create the cache entry.
The cumulative number of input tokens read from the cache.
The cumulative number of input tokens which were used.
The cumulative number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
class MessageParam: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ThinkingBlockParam: …
type: Literal["thinking"]
class RedactedThinkingBlockParam: …
type: Literal["redacted_thinking"]
class ToolUseBlockParam: …
type: Literal["tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolResultBlockParam: …
type: Literal["tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
content: Optional[Union[str, List[Content], null]]
Content = List[Content]
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ServerToolUseBlockParam: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class WebSearchToolResultBlockParam: …
type: Literal["web_search_result"]
class WebSearchToolRequestError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
role: Literal["user", "assistant"]
class MessageTokensCount: …
The total number of tokens across the provided list of messages, system prompt, and tools.
class Metadata: …
An external identifier for the user who is associated with the request.
This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.
Model = Union[Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more], str]The model that will complete your prompt.
See models for additional details and options.
The model that will complete your prompt.
See models for additional details and options.
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class TextDelta: …
type: Literal["text_delta"]
class InputJSONDelta: …
type: Literal["input_json_delta"]
class CitationsDelta: …
citation: Citation
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["citations_delta"]
class ThinkingDelta: …
type: Literal["thinking_delta"]
class SignatureDelta: …
type: Literal["signature_delta"]
class RawContentBlockDeltaEvent: …
class TextDelta: …
type: Literal["text_delta"]
class InputJSONDelta: …
type: Literal["input_json_delta"]
class CitationsDelta: …
citation: Citation
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["citations_delta"]
class ThinkingDelta: …
type: Literal["thinking_delta"]
class SignatureDelta: …
type: Literal["signature_delta"]
type: Literal["content_block_delta"]
class RawContentBlockStartEvent: …
content_block: ContentBlock
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
type: Literal["content_block_start"]
class RawContentBlockStopEvent: …
type: Literal["content_block_stop"]
class RawMessageDeltaEvent: …
delta: Delta
stop_reason: Optional[StopReason]
type: Literal["message_delta"]
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
The cumulative number of input tokens used to create the cache entry.
The cumulative number of input tokens read from the cache.
The cumulative number of input tokens which were used.
The cumulative number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
class RawMessageStartEvent: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
type: Literal["message_start"]
class RawMessageStopEvent: …
type: Literal["message_stop"]
class RawMessageStartEvent: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
type: Literal["message_start"]
class RawMessageDeltaEvent: …
delta: Delta
stop_reason: Optional[StopReason]
type: Literal["message_delta"]
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
The cumulative number of input tokens used to create the cache entry.
The cumulative number of input tokens read from the cache.
The cumulative number of input tokens which were used.
The cumulative number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
class RawMessageStopEvent: …
type: Literal["message_stop"]
class RawContentBlockStartEvent: …
content_block: ContentBlock
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
type: Literal["content_block_start"]
class RawContentBlockDeltaEvent: …
class TextDelta: …
type: Literal["text_delta"]
class InputJSONDelta: …
type: Literal["input_json_delta"]
class CitationsDelta: …
citation: Citation
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["citations_delta"]
class ThinkingDelta: …
type: Literal["thinking_delta"]
class SignatureDelta: …
type: Literal["signature_delta"]
type: Literal["content_block_delta"]
class RawContentBlockStopEvent: …
type: Literal["content_block_stop"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class RedactedThinkingBlockParam: …
type: Literal["redacted_thinking"]
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ServerToolUsage: …
The number of web search tool requests.
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class ServerToolUseBlockParam: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class SignatureDelta: …
type: Literal["signature_delta"]
StopReason = Literal["end_turn", "max_tokens", "stop_sequence", 3 more]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class TextDelta: …
type: Literal["text_delta"]
class ThinkingBlock: …
type: Literal["thinking"]
class ThinkingBlockParam: …
type: Literal["thinking"]
class ThinkingConfigDisabled: …
type: Literal["disabled"]
class ThinkingConfigEnabled: …
Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.
Must be ≥1024 and less than max_tokens.
See extended thinking for details.
type: Literal["enabled"]
Configuration for enabling Claude's extended thinking.
When enabled, responses include thinking content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your max_tokens limit.
See extended thinking for details.
Configuration for enabling Claude's extended thinking.
When enabled, responses include thinking content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your max_tokens limit.
See extended thinking for details.
class ThinkingConfigEnabled: …
Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.
Must be ≥1024 and less than max_tokens.
See extended thinking for details.
type: Literal["enabled"]
class ThinkingConfigDisabled: …
type: Literal["disabled"]
class ThinkingDelta: …
type: Literal["thinking_delta"]
class Tool: …
input_schema: InputSchemaJSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
JSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
type: Literal["object"]
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Description of what this tool does.
Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema.
type: Optional[Literal["custom"]]
class ToolBash20250124: …
name: Literal["bash"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["bash_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
class ToolChoiceAuto: …The model will automatically decide whether to use tools.
The model will automatically decide whether to use tools.
type: Literal["auto"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output at most one tool use.
class ToolChoiceAny: …The model will use any available tools.
The model will use any available tools.
type: Literal["any"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
class ToolChoiceTool: …The model will use the specified tool with tool_choice.name.
The model will use the specified tool with tool_choice.name.
The name of the tool to use.
type: Literal["tool"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
class ToolChoiceNone: …The model will not be allowed to use tools.
The model will not be allowed to use tools.
type: Literal["none"]
class ToolChoiceAny: …The model will use any available tools.
The model will use any available tools.
type: Literal["any"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
class ToolChoiceAuto: …The model will automatically decide whether to use tools.
The model will automatically decide whether to use tools.
type: Literal["auto"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output at most one tool use.
class ToolChoiceNone: …The model will not be allowed to use tools.
The model will not be allowed to use tools.
type: Literal["none"]
class ToolChoiceTool: …The model will use the specified tool with tool_choice.name.
The model will use the specified tool with tool_choice.name.
The name of the tool to use.
type: Literal["tool"]
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
class ToolResultBlockParam: …
type: Literal["tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
content: Optional[Union[str, List[Content], null]]
Content = List[Content]
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class SearchResultBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
type: Literal["search_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class DocumentBlockParam: …
source: Source
class Base64PDFSource: …
media_type: Literal["application/pdf"]
type: Literal["base64"]
class PlainTextSource: …
media_type: Literal["text/plain"]
type: Literal["text"]
class ContentBlockSource: …
class TextBlockParam: …
type: Literal["text"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class CitationCharLocationParam: …
type: Literal["char_location"]
class CitationPageLocationParam: …
type: Literal["page_location"]
class CitationContentBlockLocationParam: …
type: Literal["content_block_location"]
class CitationWebSearchResultLocationParam: …
type: Literal["web_search_result_location"]
class CitationSearchResultLocationParam: …
type: Literal["search_result_location"]
class ImageBlockParam: …
source: Source
class Base64ImageSource: …
media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]
type: Literal["base64"]
class URLImageSource: …
type: Literal["url"]
type: Literal["image"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["content"]
class URLPDFSource: …
type: Literal["url"]
type: Literal["document"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
citations: Optional[CitationsConfigParam]
class ToolTextEditor20250124: …
name: Literal["str_replace_editor"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250429: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250429"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250728: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250728"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.
class Tool: …
input_schema: InputSchemaJSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
JSON schema for this tool's input.
This defines the shape of the input that your tool accepts and that the model will produce.
type: Literal["object"]
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Description of what this tool does.
Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema.
type: Optional[Literal["custom"]]
class ToolBash20250124: …
name: Literal["bash"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["bash_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250124: …
name: Literal["str_replace_editor"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250124"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250429: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250429"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class ToolTextEditor20250728: …
name: Literal["str_replace_based_edit_tool"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["text_editor_20250728"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.
class WebSearchTool20250305: …
name: Literal["web_search"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["web_search_20250305"]
If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.
If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of times the tool can be used in the API request.
user_location: Optional[UserLocation]Parameters for the user's location. Used to provide more relevant search results.
Parameters for the user's location. Used to provide more relevant search results.
type: Literal["approximate"]
The city of the user.
The region of the user.
class ToolUseBlock: …
type: Literal["tool_use"]
class ToolUseBlockParam: …
type: Literal["tool_use"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
class URLImageSource: …
type: Literal["url"]
class URLPDFSource: …
type: Literal["url"]
class Usage: …
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
class WebSearchResultBlock: …
type: Literal["web_search_result"]
class WebSearchResultBlockParam: …
type: Literal["web_search_result"]
class WebSearchTool20250305: …
name: Literal["web_search"]Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
type: Literal["web_search_20250305"]
If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.
If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
Maximum number of times the tool can be used in the API request.
user_location: Optional[UserLocation]Parameters for the user's location. Used to provide more relevant search results.
Parameters for the user's location. Used to provide more relevant search results.
type: Literal["approximate"]
The city of the user.
The region of the user.
class WebSearchToolRequestError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
class WebSearchToolResultBlockParam: …
type: Literal["web_search_result"]
class WebSearchToolRequestError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_tool_result"]
cache_control: Optional[CacheControlEphemeral]Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
type: Literal["ephemeral"]
ttl: Optional[Literal["5m", "1h"]]The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes
1h: 1 hour
Defaults to 5m.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
type: Literal["web_search_result"]
class WebSearchToolRequestError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
MessagesBatches
Cancel a Message Batch
Create a Message Batch
Delete a Message Batch
List Message Batches
Retrieve Message Batch results
Retrieve a Message Batch
ModelsExpand Collapse
class DeletedMessageBatch: …
ID of the Message Batch.
type: Literal["message_batch_deleted"]Deleted object type.
For Message Batches, this is always "message_batch_deleted".
Deleted object type.
For Message Batches, this is always "message_batch_deleted".
class MessageBatch: …
Unique object identifier.
The format and length of IDs may change over time.
RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.
RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.
RFC 3339 datetime string representing the time at which the Message Batch was created.
RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends.
Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired.
RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation.
processing_status: Literal["in_progress", "canceling", "ended"]Processing status of the Message Batch.
Processing status of the Message Batch.
Tallies requests within the Message Batch, categorized by their status.
Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.
Tallies requests within the Message Batch, categorized by their status.
Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.
Number of requests in the Message Batch that have been canceled.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that encountered an error.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that have expired.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that are processing.
Number of requests in the Message Batch that have completed successfully.
This is zero until processing of the entire Message Batch has ended.
URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.
Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.
type: Literal["message_batch"]Object type.
For Message Batches, this is always "message_batch".
Object type.
For Message Batches, this is always "message_batch".
class MessageBatchCanceledResult: …
type: Literal["canceled"]
class MessageBatchErroredResult: …
class InvalidRequestError: …
type: Literal["invalid_request_error"]
class AuthenticationError: …
type: Literal["authentication_error"]
class BillingError: …
type: Literal["billing_error"]
class PermissionError: …
type: Literal["permission_error"]
class NotFoundError: …
type: Literal["not_found_error"]
class RateLimitError: …
type: Literal["rate_limit_error"]
class GatewayTimeoutError: …
type: Literal["timeout_error"]
class APIErrorObject: …
type: Literal["api_error"]
class OverloadedError: …
type: Literal["overloaded_error"]
type: Literal["error"]
type: Literal["errored"]
class MessageBatchExpiredResult: …
type: Literal["expired"]
class MessageBatchIndividualResponse: …This is a single line in the response .jsonl file and does not represent the response as a whole.
This is a single line in the response .jsonl file and does not represent the response as a whole.
Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order.
Must be unique for each request within the Message Batch.
Processing result for this request.
Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.
Processing result for this request.
Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.
class MessageBatchSucceededResult: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
type: Literal["succeeded"]
class MessageBatchErroredResult: …
class InvalidRequestError: …
type: Literal["invalid_request_error"]
class AuthenticationError: …
type: Literal["authentication_error"]
class BillingError: …
type: Literal["billing_error"]
class PermissionError: …
type: Literal["permission_error"]
class NotFoundError: …
type: Literal["not_found_error"]
class RateLimitError: …
type: Literal["rate_limit_error"]
class GatewayTimeoutError: …
type: Literal["timeout_error"]
class APIErrorObject: …
type: Literal["api_error"]
class OverloadedError: …
type: Literal["overloaded_error"]
type: Literal["error"]
type: Literal["errored"]
class MessageBatchCanceledResult: …
type: Literal["canceled"]
class MessageBatchExpiredResult: …
type: Literal["expired"]
class MessageBatchRequestCounts: …
Number of requests in the Message Batch that have been canceled.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that encountered an error.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that have expired.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that are processing.
Number of requests in the Message Batch that have completed successfully.
This is zero until processing of the entire Message Batch has ended.
Processing result for this request.
Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.
Processing result for this request.
Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.
class MessageBatchSucceededResult: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
type: Literal["succeeded"]
class MessageBatchErroredResult: …
class InvalidRequestError: …
type: Literal["invalid_request_error"]
class AuthenticationError: …
type: Literal["authentication_error"]
class BillingError: …
type: Literal["billing_error"]
class PermissionError: …
type: Literal["permission_error"]
class NotFoundError: …
type: Literal["not_found_error"]
class RateLimitError: …
type: Literal["rate_limit_error"]
class GatewayTimeoutError: …
type: Literal["timeout_error"]
class APIErrorObject: …
type: Literal["api_error"]
class OverloadedError: …
type: Literal["overloaded_error"]
type: Literal["error"]
type: Literal["errored"]
class MessageBatchCanceledResult: …
type: Literal["canceled"]
class MessageBatchExpiredResult: …
type: Literal["expired"]
class MessageBatchSucceededResult: …
Unique object identifier.
The format and length of IDs may change over time.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
class TextBlock: …
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
Citations supporting the text block.
The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.
class CitationCharLocation: …
type: Literal["char_location"]
class CitationPageLocation: …
type: Literal["page_location"]
class CitationContentBlockLocation: …
type: Literal["content_block_location"]
class CitationsWebSearchResultLocation: …
type: Literal["web_search_result_location"]
class CitationsSearchResultLocation: …
type: Literal["search_result_location"]
type: Literal["text"]
class ThinkingBlock: …
type: Literal["thinking"]
class RedactedThinkingBlock: …
type: Literal["redacted_thinking"]
class ToolUseBlock: …
type: Literal["tool_use"]
class ServerToolUseBlock: …
name: Literal["web_search"]
type: Literal["server_tool_use"]
class WebSearchToolResultBlock: …
class WebSearchToolResultError: …
error_code: Literal["invalid_tool_input", "unavailable", "max_uses_exceeded", 2 more]
type: Literal["web_search_tool_result_error"]
type: Literal["web_search_result"]
type: Literal["web_search_tool_result"]
UnionMember0 = Literal["claude-3-7-sonnet-latest", "claude-3-7-sonnet-20250219", "claude-3-5-haiku-latest", 15 more]The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-7-sonnet-20250219 - Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-5-haiku-latest - Fastest and most compact model for near-instant responsiveness
claude-3-5-haiku-20241022 - Our fastest model
claude-haiku-4-5 - Hybrid model, capable of near-instant responses and extended thinking
claude-haiku-4-5-20251001 - Hybrid model, capable of near-instant responses and extended thinking
claude-sonnet-4-20250514 - High-performance model with extended thinking
claude-sonnet-4-0 - High-performance model with extended thinking
claude-4-sonnet-20250514 - High-performance model with extended thinking
claude-sonnet-4-5 - Our best model for real-world agents and coding
claude-sonnet-4-5-20250929 - Our best model for real-world agents and coding
claude-opus-4-0 - Our most capable model
claude-opus-4-20250514 - Our most capable model
claude-4-opus-20250514 - Our most capable model
claude-opus-4-1-20250805 - Our most capable model
claude-3-opus-latest - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-opus-20240229 - Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
claude-3-haiku-20240307 - Our previous most fast and cost-effective
The model that will complete your prompt.
See models for additional details and options.
claude-3-7-sonnet-latest- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-7-sonnet-20250219- Deprecated: Will reach end-of-life on February 19th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-5-haiku-latest- Fastest and most compact model for near-instant responsivenessclaude-3-5-haiku-20241022- Our fastest modelclaude-haiku-4-5- Hybrid model, capable of near-instant responses and extended thinkingclaude-haiku-4-5-20251001- Hybrid model, capable of near-instant responses and extended thinkingclaude-sonnet-4-20250514- High-performance model with extended thinkingclaude-sonnet-4-0- High-performance model with extended thinkingclaude-4-sonnet-20250514- High-performance model with extended thinkingclaude-sonnet-4-5- Our best model for real-world agents and codingclaude-sonnet-4-5-20250929- Our best model for real-world agents and codingclaude-opus-4-0- Our most capable modelclaude-opus-4-20250514- Our most capable modelclaude-4-opus-20250514- Our most capable modelclaude-opus-4-1-20250805- Our most capable modelclaude-3-opus-latest- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-opus-20240229- Deprecated: Will reach end-of-life on January 5th, 2026. Please migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.claude-3-haiku-20240307- Our previous most fast and cost-effective
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: Literal["assistant"]Conversational role of the generated message.
This will always be "assistant".
Conversational role of the generated message.
This will always be "assistant".
stop_reason: Optional[StopReason]The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
The reason that we stopped.
This may be one the following values:
"end_turn": the model reached a natural stopping point"max_tokens": we exceeded the requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas generated"tool_use": the model invoked one or more tools"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue."refusal": when streaming classifiers intervene to handle potential policy violations
In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: Literal["message"]Object type.
For Messages, this is always "message".
Object type.
For Messages, this is always "message".
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
Billing and rate-limit usage.
Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.
Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.
For example, output_tokens will be non-zero, even for an empty string response from Claude.
Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.
cache_creation: Optional[CacheCreation]Breakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
server_tool_use: Optional[ServerToolUsage]The number of server tool requests.
The number of server tool requests.
The number of web search tool requests.
service_tier: Optional[Literal["standard", "priority", "batch"]]If the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.