Count tokens for an Anthropic message
curl --request POST \
--url https://api.sailresearch.com/v1/messages/count_tokens \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"content": "<string>"
}
],
"max_tokens": 2,
"system": "<string>",
"temperature": 0.5,
"top_p": 0.5,
"output_config": {},
"routing": {
"allowed_countries": [
"<string>"
]
},
"tools": [
{}
],
"tool_choice": {},
"thinking": {},
"metadata": {
"completion_webhook": "<string>",
"webhook_token": "<string>",
"supercache_write": "24h"
},
"context_management": {},
"cache_control": {
"type": "ephemeral"
}
}
'import requests
url = "https://api.sailresearch.com/v1/messages/count_tokens"
payload = {
"model": "<string>",
"messages": [{ "content": "<string>" }],
"max_tokens": 2,
"system": "<string>",
"temperature": 0.5,
"top_p": 0.5,
"output_config": {},
"routing": { "allowed_countries": ["<string>"] },
"tools": [{}],
"tool_choice": {},
"thinking": {},
"metadata": {
"completion_webhook": "<string>",
"webhook_token": "<string>",
"supercache_write": "24h"
},
"context_management": {},
"cache_control": { "type": "ephemeral" }
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
messages: [{content: '<string>'}],
max_tokens: 2,
system: '<string>',
temperature: 0.5,
top_p: 0.5,
output_config: {},
routing: {allowed_countries: ['<string>']},
tools: [{}],
tool_choice: {},
thinking: {},
metadata: {
completion_webhook: '<string>',
webhook_token: '<string>',
supercache_write: '24h'
},
context_management: {},
cache_control: {type: 'ephemeral'}
})
};
fetch('https://api.sailresearch.com/v1/messages/count_tokens', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.sailresearch.com/v1/messages/count_tokens",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => '<string>',
'messages' => [
[
'content' => '<string>'
]
],
'max_tokens' => 2,
'system' => '<string>',
'temperature' => 0.5,
'top_p' => 0.5,
'output_config' => [
],
'routing' => [
'allowed_countries' => [
'<string>'
]
],
'tools' => [
[
]
],
'tool_choice' => [
],
'thinking' => [
],
'metadata' => [
'completion_webhook' => '<string>',
'webhook_token' => '<string>',
'supercache_write' => '24h'
],
'context_management' => [
],
'cache_control' => [
'type' => 'ephemeral'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.sailresearch.com/v1/messages/count_tokens"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.sailresearch.com/v1/messages/count_tokens")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.sailresearch.com/v1/messages/count_tokens")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}"
response = http.request(request)
puts response.read_body{
"input_tokens": 123
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}Messages API
Count tokens for an Anthropic message
Counts the input tokens a create-message request would consume, without running the model.
POST
/
messages
/
count_tokens
Count tokens for an Anthropic message
curl --request POST \
--url https://api.sailresearch.com/v1/messages/count_tokens \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"content": "<string>"
}
],
"max_tokens": 2,
"system": "<string>",
"temperature": 0.5,
"top_p": 0.5,
"output_config": {},
"routing": {
"allowed_countries": [
"<string>"
]
},
"tools": [
{}
],
"tool_choice": {},
"thinking": {},
"metadata": {
"completion_webhook": "<string>",
"webhook_token": "<string>",
"supercache_write": "24h"
},
"context_management": {},
"cache_control": {
"type": "ephemeral"
}
}
'import requests
url = "https://api.sailresearch.com/v1/messages/count_tokens"
payload = {
"model": "<string>",
"messages": [{ "content": "<string>" }],
"max_tokens": 2,
"system": "<string>",
"temperature": 0.5,
"top_p": 0.5,
"output_config": {},
"routing": { "allowed_countries": ["<string>"] },
"tools": [{}],
"tool_choice": {},
"thinking": {},
"metadata": {
"completion_webhook": "<string>",
"webhook_token": "<string>",
"supercache_write": "24h"
},
"context_management": {},
"cache_control": { "type": "ephemeral" }
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
messages: [{content: '<string>'}],
max_tokens: 2,
system: '<string>',
temperature: 0.5,
top_p: 0.5,
output_config: {},
routing: {allowed_countries: ['<string>']},
tools: [{}],
tool_choice: {},
thinking: {},
metadata: {
completion_webhook: '<string>',
webhook_token: '<string>',
supercache_write: '24h'
},
context_management: {},
cache_control: {type: 'ephemeral'}
})
};
fetch('https://api.sailresearch.com/v1/messages/count_tokens', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.sailresearch.com/v1/messages/count_tokens",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => '<string>',
'messages' => [
[
'content' => '<string>'
]
],
'max_tokens' => 2,
'system' => '<string>',
'temperature' => 0.5,
'top_p' => 0.5,
'output_config' => [
],
'routing' => [
'allowed_countries' => [
'<string>'
]
],
'tools' => [
[
]
],
'tool_choice' => [
],
'thinking' => [
],
'metadata' => [
'completion_webhook' => '<string>',
'webhook_token' => '<string>',
'supercache_write' => '24h'
],
'context_management' => [
],
'cache_control' => [
'type' => 'ephemeral'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.sailresearch.com/v1/messages/count_tokens"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.sailresearch.com/v1/messages/count_tokens")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.sailresearch.com/v1/messages/count_tokens")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"max_tokens\": 2,\n \"system\": \"<string>\",\n \"temperature\": 0.5,\n \"top_p\": 0.5,\n \"output_config\": {},\n \"routing\": {\n \"allowed_countries\": [\n \"<string>\"\n ]\n },\n \"tools\": [\n {}\n ],\n \"tool_choice\": {},\n \"thinking\": {},\n \"metadata\": {\n \"completion_webhook\": \"<string>\",\n \"webhook_token\": \"<string>\",\n \"supercache_write\": \"24h\"\n },\n \"context_management\": {},\n \"cache_control\": {\n \"type\": \"ephemeral\"\n }\n}"
response = http.request(request)
puts response.read_body{
"input_tokens": 123
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}{
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "<string>"
},
"request_id": "<string>"
}Authorizations
BearerAuthAnthropicApiKey
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Same shape as a create-message request; max_tokens is optional and ignored for counting.
Minimum array length:
1Show child attributes
Show child attributes
Optional here; validated if present, not used for counting.
Required range:
x >= 1System prompt: a string, or an array of text blocks.
Required range:
0 <= x <= 1Required range:
0 <= x <= 1Show child attributes
Show child attributes
Show child attributes
Show child attributes
Tool definitions the model may call. Responses include tool_use blocks; return outcomes as tool_result content blocks in a follow-up message.
Controls tool use: auto, any, tool, or none.
Extended thinking configuration; translated to the model's reasoning.
Optional string metadata. completion_window controls scheduling; completion_webhook/webhook_token configure completion webhooks; supercache_write stores a reusable prompt prefix.
Show child attributes
Show child attributes
Anthropic server-side context-editing config (Claude Code sends it automatically). Accepted for compatibility but ignored: Sail forwards the full context each turn.
Prompt-cache breakpoint (e.g. { "type": "ephemeral" }). Accepted for Anthropic SDK compatibility and has no effect: Sail caches repeated prompt prefixes automatically, without breakpoints. Cache reads are reported in usage.cache_read_input_tokens.
Show child attributes
Show child attributes
Response
Input token count.