Mulai 29 April 2025, model Gemini 1.5 Pro dan Gemini 1.5 Flash tidak tersedia di project yang belum pernah menggunakan model ini, termasuk project baru. Untuk mengetahui detailnya, lihat Versi dan siklus proses model.
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Endpoint count-tokens memungkinkan Anda menentukan jumlah token dalam pesan sebelum mengirimkannya ke Claude, sehingga membantu Anda membuat keputusan yang tepat tentang perintah dan penggunaan Anda.
Tidak ada biaya untuk menggunakan endpoint count-tokens.
ROLE: Peran yang terkait dengan
pesan. Anda dapat menentukan user atau assistant.
Pesan pertama harus menggunakan peran user. Model Claude
beroperasi dengan giliran user dan assistant yang bergantian.
Jika pesan terakhir menggunakan peran assistant, maka konten respons
akan langsung dilanjutkan dari konten dalam pesan tersebut. Anda dapat menggunakan
ini untuk membatasi sebagian respons model.
CONTENT: Konten, seperti teks, dari pesan user atau
assistant.
Metode HTTP dan URL:
POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/count-tokens:rawPredict
Isi JSON permintaan:
{
"model": "MODEL",
"messages": [
{
"role": "user",
"content":"how many tokens are in this request?"
}
],
}
Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:
curl
Simpan isi permintaan dalam file bernama request.json,
dan jalankan perintah berikut:
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-04 UTC."],[],[],null,["# Count tokens for Claude models\n\nThe `count-tokens` endpoint lets you determine the number of tokens in a\nmessage before sending it to Claude, helping you make informed decisions about\nyour prompts and usage.\n\nThere is no cost for using the `count-tokens` endpoint.\n\nSupported Claude models\n-----------------------\n\nThe following models support count tokens:\n\n- [Claude Opus 4.1](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-opus-4-1)\n- [Claude Opus 4](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-opus-4)\n- [Claude Sonnet 4](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-sonnet-4)\n- [Claude 3.7 Sonnet](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-7-sonnet)\n- [Claude 3.5 Sonnet v2](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-sonnet-v2)\n- [Claude 3.5 Haiku](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-haiku)\n- [Claude 3.5 Sonnet](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-sonnet)\n- [Claude 3 Opus](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-opus)\n- [Claude 3 Haiku](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-haiku)\n\n\u003cbr /\u003e\n\nSupported regions\n-----------------\n\nThe following regions support count tokens:\n\n- `us-east5`\n- `europe-west1`\n- `asia-east1`\n- `asia-southeast1`\n- `us-central1`\n- `europe-west4`\n\nCount tokens in basic messages\n------------------------------\n\nTo count tokens, send a `rawPredict` request to the `count-tokens` endpoint. The\nbody of the request must contain the model ID of the model you want to count\ntokens against. \n\n### REST\n\n\nBefore using any of the request data,\nmake the following replacements:\n\n- \u003cvar class=\"edit\" scope=\"LOCATION\" translate=\"no\"\u003eLOCATION\u003c/var\u003e: A [region](#regions) that supports Anthropic Claude models. To use the global endpoint, see [Specify\n the global endpoint](/vertex-ai/generative-ai/docs/partner-models/use-partner-models#global).\n- \u003cvar class=\"edit\" scope=\"MODEL\" translate=\"no\"\u003eMODEL\u003c/var\u003e: The [model](#model-list) to count tokens against.\n- \u003cvar translate=\"no\"\u003eROLE\u003c/var\u003e: The role associated with a message. You can specify a `user` or an `assistant`. The first message must use the `user` role. Claude models operate with alternating `user` and `assistant` turns. If the final message uses the `assistant` role, then the response content continues immediately from the content in that message. You can use this to constrain part of the model's response.\n- \u003cvar translate=\"no\"\u003eCONTENT\u003c/var\u003e: The content, such as text, of the `user` or `assistant` message.\n\n\nHTTP method and URL:\n\n```\nPOST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/count-tokens:rawPredict\n```\n\n\nRequest JSON body:\n\n```\n{\n \"model\": \"MODEL\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\":\"how many tokens are in this request?\"\n }\n ],\n}\n```\n\nTo send your request, choose one of these options: \n\n#### curl\n\n| **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](/sdk/gcloud/reference/init) or [`gcloud auth login`](/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](/sdk/gcloud/reference/auth/list).\n\n\nSave the request body in a file named `request.json`,\nand execute the following command:\n\n```\ncurl -X POST \\\n -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n -H \"Content-Type: application/json; charset=utf-8\" \\\n -d @request.json \\\n \"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/count-tokens:rawPredict\"\n```\n\n#### PowerShell\n\n| **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](/sdk/gcloud/reference/init) or [`gcloud auth login`](/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](/sdk/gcloud/reference/auth/list).\n\n\nSave the request body in a file named `request.json`,\nand execute the following command:\n\n```\n$cred = gcloud auth print-access-token\n$headers = @{ \"Authorization\" = \"Bearer $cred\" }\n\nInvoke-WebRequest `\n -Method POST `\n -Headers $headers `\n -ContentType: \"application/json; charset=utf-8\" `\n -InFile request.json `\n -Uri \"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/count-tokens:rawPredict\" | Select-Object -Expand Content\n```\n\nYou should receive a JSON response similar to the following.\n\n#### Response\n\n```\n{ \"input_tokens\": 14 }\n```\n\n\u003cbr /\u003e\n\nFor information on how to count tokens in messages with tools, images, and PDFs,\nsee [Anthropic's documentation](https://docs.anthropic.com/en/docs/build-with-claude/token-counting).\n\nQuotas\n------\n\nBy default, the quota for the `count-tokens` endpoint is 2000 requests per\nminute."]]
