Token counting

POST /v1/messages/count_tokens  compatible  semantic operation generate  contract revision 1

State semantics: stateless; served natively against one direct Anthropic connection

Raw contract deviations

These statements are source-contract evidence. Use the examples, field table, and Profile coverage matrix for ordinary integration, and expand this list when investigating a compatibility boundary.

• only the direct Anthropic Messages provider profile serves this endpoint; Bedrock Mantle shares the Messages wire format but its count_tokens surface is not established
• the request body reaches the provider verbatim with only the upstream model identifier substituted, so there is no portable execution mode to select
• count_tokens has no input/output token billing span, so Halro settles zero under ordinary per-token prices; a configured fixed per-request fee is still charged — it is a real provider call on the operator’s credential, so it takes a ledger attempt and appears in the audit trail like any other
• the reported count is Anthropic’s, for the upstream model behind the alias; it is not re-derived by Halro

Count tokens before generation. This endpoint does not stream and rejects Halro-Route-Mode: portable.

A fixed per-request fee still settles

Count Tokens has no input/output token billing span, so ordinary token prices settle to zero. If the Price Version defines a fixed per-request fee, that fee is still written to the ledger.

Request examples

curl

curl https://halro.example.com/v1/messages/count_tokens \
  -H "x-api-key: $HALRO_GATEWAY_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{ "model": "claude",
        "messages": [{"role": "user", "content": "Hello"}] }'

Python

import os
from anthropic import Anthropic

client = Anthropic(base_url="https://halro.example.com", api_key=os.environ["HALRO_GATEWAY_KEY"],
                   timeout=60.0, max_retries=0)
count = client.messages.count_tokens(
    model="claude",
    messages=[{"role": "user", "content": "Hello"}],
)
print(count.input_tokens)

Node.js

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://halro.example.com", apiKey: process.env.HALRO_GATEWAY_KEY,
  timeout: 60_000, maxRetries: 0,
});
const count = await client.messages.countTokens({
  model: "claude",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(count.input_tokens);

SDK retries are enabled by default

Official SDKs normally retry twice. Halro persists the budget reservation before Provider I/O, so a silent client retry creates separate reservations and settlements. The examples disable SDK retries; own the retry policy using Retries, timeouts, and idempotency.

Request headers

• x-api-key or Authorization
• anthropic-version
• anthropic-beta
• Content-Type

Request fields

How to read this table

Silence in column two does not mean verified support. The contract records declared limits; a Profile with no listed restriction remains undeclared, not proven compatible. Column three records value- or combination-level rejections that cannot be represented by a field-only matrix. Types, required relationships, and value semantics are not yet carried by this contract.

Request fields

Field	Provider Profiles that do not support it	Combination-level constraints
model	—	—
messages	—	—
messages[].role	—	—
messages[].content	—	—
system	—	—
tools	—	—
tool_choice	—	—
thinking	—	—
output_config	—	—

Fields rejected at the facade

Halro rejects these fields before any Provider I/O:

• stream
• Halro-Route-Mode: portable
• unknown top-level fields

Response fields

input_tokens

Provider Profile contract coverage and current availability

Endpoint maturity does not promote a Profile

The compatible badge describes the endpoint. Every Profile row retains its own coverage maturity.

Provider Profile contract coverage and current availability

Provider Profile	Maturity	Current build	Unsupported request fields
anthropic.messages.2023-06-01	compatible	creatable	undeclared

Declared transformations

anthropic.messages.2023-06-01

• only the model identifier is substituted; every other member is forwarded unchanged

Evidence

Verified evidence: gateway_contract, provider_transport_fixture, sdk_blackbox

SDK black-box protocol-stub matrix

anthropic-go, anthropic-typescript, anthropic-python

Caution

This matrix proves that listed SDK versions serialize requests and consume Halro’s declared response and stream shapes. It uses protocol stubs and does not exercise live Runtime routing, Gateway Key authentication, capability filtering, redaction, budget accounting, or a real Provider.

Best practices

See Anthropic native features and Token Count.

---

Fields, coverage, transformations, and deviations are generated from Halro 8f185de7674c (scripts/generate-api-pages-en.mjs; synchronized manifest digest 8e5e7a0a794721aa…). The synchronized copy contains 1 recorded accuracy correction(s); source manifest digest b321ee18ad2e38f3…. The contract currently carries field names, not complete types, required relationships, or value semantics.