Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Cohere ai Cohere python ApiMetaBilledUnits Model

From Leeroopedia
Knowledge Sources
Domains SDK, Billing
Last Updated 2026-02-15 14:00 GMT

Overview

The ApiMetaBilledUnits class is a Pydantic model representing the breakdown of billed units in a Cohere API response.

Description

The ApiMetaBilledUnits model provides a detailed breakdown of all units billed for a given API request. It tracks six categories of billable usage: images, input tokens, image tokens, output tokens, search units, and classifications. All fields are optional floats since not every API call incurs charges across all categories. This model extends UncheckedBaseModel and is auto-generated from the Cohere API definition by Fern. It is typically nested within the ApiMeta model as the billed_units field.

Usage

Use this model to monitor and audit billing consumption after API calls. It is particularly useful for cost tracking, usage analytics, and budget management when integrating Cohere services into production applications.

Code Reference

Source Location

Signature

class ApiMetaBilledUnits(UncheckedBaseModel):
    images: typing.Optional[float] = pydantic.Field(default=None)
    input_tokens: typing.Optional[float] = pydantic.Field(default=None)
    image_tokens: typing.Optional[float] = pydantic.Field(default=None)
    output_tokens: typing.Optional[float] = pydantic.Field(default=None)
    search_units: typing.Optional[float] = pydantic.Field(default=None)
    classifications: typing.Optional[float] = pydantic.Field(default=None)

Import

from cohere.types import ApiMetaBilledUnits

I/O Contract

Field Type Required Default Description
images Optional[float] No None The number of billed images.
input_tokens Optional[float] No None The number of billed input tokens.
image_tokens Optional[float] No None The number of billed image tokens.
output_tokens Optional[float] No None The number of billed output tokens.
search_units Optional[float] No None The number of billed search units.
classifications Optional[float] No None The number of billed classification units.

Usage Examples

import cohere

client = cohere.Client(api_key="YOUR_API_KEY")

response = client.chat(
    model="command-r-plus",
    message="What is the capital of France?",
)

# Access billed units from the response metadata
billed = response.meta.billed_units

if billed is not None:
    print(f"Input tokens billed: {billed.input_tokens}")
    print(f"Output tokens billed: {billed.output_tokens}")
    print(f"Search units billed: {billed.search_units}")
    print(f"Images billed: {billed.images}")
    print(f"Image tokens billed: {billed.image_tokens}")
    print(f"Classifications billed: {billed.classifications}")

    # Calculate total token cost
    total_tokens = (billed.input_tokens or 0) + (billed.output_tokens or 0)
    print(f"Total tokens: {total_tokens}")

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment