Count tokens in a Message
Count the number of tokens in a Message.
The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it.
Learn more about token counting in our user guide
ParametersExpand Collapse
body MessageCountTokensParams
Messages param.Field[[]MessageParamResp]
Input messages.
Our models are trained to operate on alternating user and assistant conversational turns. When creating a new Message, you specify the prior conversational turns with the messages parameter, and the model then generates the next Message in the conversation. Consecutive user or assistant turns in your request will be combined into a single turn.
Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages.
If the final message uses the assistant role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.
Example with a single user message:
[{"role": "user", "content": "Hello, Claude"}]
Example with multiple conversational turns:
[
{"role": "user", "content": "Hello there."},
{"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"},
{"role": "user", "content": "Can you explain LLMs in plain English?"},
]
Example with a partially-filled response from Claude:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("},
]
Each input message content may be either a single string or an array of content blocks, where each block has a specific type. Using a string for content is shorthand for an array of one content block of type "text". The following input messages are equivalent:
{"role": "user", "content": "Hello, Claude"}
{"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]}
See input examples.
Note that if you want to include a system prompt, you can use the top-level system parameter — there is no "system" role for input messages in the Messages API.
There is a limit of 100,000 messages in a single request.
Content []ContentBlockParamUnionResp
type TextBlockParamResp struct{…}
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
type ImageBlockParamResp struct{…}
Source ImageBlockParamSourceUnionResp
type Base64ImageSource struct{…}
MediaType Base64ImageSourceMediaType
Type Base64
type URLImageSource struct{…}
Type URL
Type Image
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 DocumentBlockParamResp struct{…}
Source DocumentBlockParamSourceUnionResp
type Base64PDFSource struct{…}
MediaType ApplicationPDF
Type Base64
type PlainTextSource struct{…}
MediaType TextPlain
Type Text
type ContentBlockSource struct{…}
Content ContentBlockSourceContentUnion
type TextBlockParamResp struct{…}
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
type ImageBlockParamResp struct{…}
Source ImageBlockParamSourceUnionResp
type Base64ImageSource struct{…}
MediaType Base64ImageSourceMediaType
Type Base64
type URLImageSource struct{…}
Type URL
Type Image
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 Content
type URLPDFSource struct{…}
Type URL
Type Document
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 SearchResultBlockParamResp struct{…}
Content []TextBlockParamResp
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
Type SearchResult
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ThinkingBlockParamResp struct{…}
Type Thinking
type RedactedThinkingBlockParamResp struct{…}
Type RedactedThinking
type ToolUseBlockParamResp struct{…}
Type ToolUse
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ToolResultBlockParamResp struct{…}
Type ToolResult
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 []ToolResultBlockParamContentUnionRespoptional
[]ToolResultBlockParamContentUnionResp
type TextBlockParamResp struct{…}
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
type ImageBlockParamResp struct{…}
Source ImageBlockParamSourceUnionResp
type Base64ImageSource struct{…}
MediaType Base64ImageSourceMediaType
Type Base64
type URLImageSource struct{…}
Type URL
Type Image
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 SearchResultBlockParamResp struct{…}
Content []TextBlockParamResp
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
Type SearchResult
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 DocumentBlockParamResp struct{…}
Source DocumentBlockParamSourceUnionResp
type Base64PDFSource struct{…}
MediaType ApplicationPDF
Type Base64
type PlainTextSource struct{…}
MediaType TextPlain
Type Text
type ContentBlockSource struct{…}
Content ContentBlockSourceContentUnion
type TextBlockParamResp struct{…}
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
type ImageBlockParamResp struct{…}
Source ImageBlockParamSourceUnionResp
type Base64ImageSource struct{…}
MediaType Base64ImageSourceMediaType
Type Base64
type URLImageSource struct{…}
Type URL
Type Image
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 Content
type URLPDFSource struct{…}
Type URL
Type Document
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ServerToolUseBlockParamResp struct{…}
Name WebSearch
Type ServerToolUse
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 WebSearchToolResultBlockParamResp struct{…}
Type WebSearchResult
type WebSearchToolRequestError struct{…}
ErrorCode WebSearchToolRequestErrorErrorCode
Type WebSearchToolResultError
Type WebSearchToolResult
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 MessageParamRole
Model param.Field[Model]
The model that will complete your prompt.
See models for additional details and options.
System prompt.
A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our guide to system prompts.
Type Text
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 CitationCharLocationParamResp struct{…}
Type CharLocation
type CitationPageLocationParamResp struct{…}
Type PageLocation
type CitationContentBlockLocationParamResp struct{…}
Type ContentBlockLocation
type CitationWebSearchResultLocationParamResp struct{…}
Type WebSearchResultLocation
type CitationSearchResultLocationParamResp struct{…}
Type SearchResultLocation
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.
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.
Definitions of tools that the model may use.
If you include tools in your API request, the model may return tool_use content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using tool_result content blocks.
There are two types of tools: client tools and server tools. The behavior described below applies to client tools. For server tools, see their individual documentation as each has its own behavior (e.g., the web search tool).
Each tool definition includes:
name: Name of the tool.description: Optional, but strongly-recommended description of the tool.input_schema: JSON schema for the toolinputshape that the model will produce intool_useoutput content blocks.
For example, if you defined tools as:
[
{
"name": "get_stock_price",
"description": "Get the current stock price for a given ticker symbol.",
"input_schema": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
}
},
"required": ["ticker"]
}
}
]
And then asked the model "What's the S&P 500 at today?", the model might produce tool_use content blocks in the response like this:
[
{
"type": "tool_use",
"id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
"name": "get_stock_price",
"input": { "ticker": "^GSPC" }
}
]
You might then run your get_stock_price tool with {"ticker": "^GSPC"} as an input, and return the following back to the model in a subsequent user message:
[
{
"type": "tool_result",
"tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
"content": "259.75 USD"
}
]
Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output.
See our guide for more details.
type Tool struct{…}
InputSchema ToolInputSchema
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 Object
Name string
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 stringoptional
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 ToolTypeoptional
type ToolBash20250124 struct{…}
Name Bash
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Type Bash20250124
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ToolTextEditor20250124 struct{…}
Name StrReplaceEditor
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Type TextEditor20250124
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ToolTextEditor20250429 struct{…}
Name StrReplaceBasedEditTool
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Type TextEditor20250429
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
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 ToolTextEditor20250728 struct{…}
Name StrReplaceBasedEditTool
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Type TextEditor20250728
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
MaxCharacters int64optional
Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.
type WebSearchTool20250305 struct{…}
Name WebSearch
Name of the tool.
This is how the tool will be called by the model and in tool_use blocks.
Type WebSearch20250305
AllowedDomains []stringoptional
If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.
BlockedDomains []stringoptional
If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.
Create a cache control breakpoint at this content block.
Type Ephemeral
TTL CacheControlEphemeralTTLoptional
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m.
MaxUses int64optional
Maximum number of times the tool can be used in the API request.
UserLocation WebSearchTool20250305UserLocationoptional
Parameters for the user's location. Used to provide more relevant search results.
Type Approximate
City stringoptional
The city of the user.
Country stringoptional
The two letter ISO country code of the user.
Region stringoptional
The region of the user.
Timezone stringoptional
The IANA timezone of the user.
ReturnsExpand Collapse
type MessageTokensCount struct{…}
InputTokens int64
The total number of tokens across the provided list of messages, system prompt, and tools.
package main
import (
"context"
"fmt"
"github.com/anthropics/anthropic-sdk-go"
"github.com/anthropics/anthropic-sdk-go/option"
)
func main() {
client := anthropic.NewClient(
option.WithAPIKey("my-anthropic-api-key"),
)
messageTokensCount, err := client.Messages.CountTokens(context.TODO(), anthropic.MessageCountTokensParams{
Messages: []anthropic.MessageParam{anthropic.MessageParam{
Content: []anthropic.ContentBlockParamUnion{anthropic.ContentBlockParamUnion{
OfText: &anthropic.TextBlockParam{Text: "What is a quaternion?", CacheControl: anthropic.CacheControlEphemeralParam{TTL: anthropic.CacheControlEphemeralTTLTTL5m}, Citations: []anthropic.TextCitationParamUnion{anthropic.TextCitationParamUnion{
OfCharLocation: &anthropic.CitationCharLocationParam{CitedText: "cited_text", DocumentIndex: 0, DocumentTitle: anthropic.String("x"), EndCharIndex: 0, StartCharIndex: 0},
}}},
}},
Role: anthropic.MessageParamRoleUser,
}},
Model: anthropic.ModelClaudeOpus4_5_20251101,
})
if err != nil {
panic(err.Error())
}
fmt.Printf("%+v\n", messageTokensCount.InputTokens)
}
{
"input_tokens": 2095
}Returns Examples
{
"input_tokens": 2095
}