APIClaw Cost Tracking API
The Cost Tracking API from APIClaw — 4 operation(s) for cost tracking.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/apiclaw:apiclaw-cost-tracking-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: LiteLLM Cost Tracking API
description: 'Proxy Server to call 100+ LLMs in the OpenAI format. **Customize Swagger Docs**
👉 ```LiteLLM Admin Panel on /ui```. Create, Edit Keys with SSO. Having issues? Try ```Fallback Login```
💸 ```LiteLLM Model Cost Map```.
🔎 ```LiteLLM Model Hub```. See available models on the proxy. **Docs**'
version: 1.105.1
tags:
- name: Cost Tracking
paths:
/cost/predict-cache:
post:
tags:
- Cost Tracking
summary: Predict Cache Cost
description: 'Compare the next native Anthropic request on two configured deployment IDs.
Estimates use provider token counting and recent successful cache telemetry for this key.
Unknown cache state uses the cold scenario when prices/counts are available. Cache observations
do not guarantee retention. v0 supports one message-content breakpoint, text and client tools;
system/tool-only breakpoints, thinking, images, nondefault Anthropic versions, beta headers and
request transforms are unknown.
Each provider count consumes one RPM unit and holds concurrency capacity; a comparison uses
up to four counts. The legacy rate limiter returns unknown without contacting the provider.
This endpoint does not generate tokens, prewarm caches, choose a model or alter routing.'
operationId: predict_cache_cost_cost_predict_cache_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CachePredictionRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/CachePredictionResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
/config/cost_discount_config:
get:
tags:
- Cost Tracking
summary: Get Cost Discount Config
description: 'Get current cost discount configuration.
Returns the cost_discount_config from litellm_settings.'
operationId: get_cost_discount_config_config_cost_discount_config_get
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
security:
- APIKeyHeader: []
patch:
tags:
- Cost Tracking
summary: Update Cost Discount Config
description: 'Update cost discount configuration.
Updates the cost_discount_config in litellm_settings.
Discounts should be between 0 and 1 (e.g., 0.05 = 5% discount).
Example:
```json
{
"vertex_ai": 0.05,
"gemini": 0.05,
"openai": 0.01
}
```'
operationId: update_cost_discount_config_config_cost_discount_config_patch
requestBody:
content:
application/json:
schema:
additionalProperties:
type: number
type: object
title: Cost Discount Config
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
/config/cost_margin_config:
get:
tags:
- Cost Tracking
summary: Get Cost Margin Config
description: 'Get current cost margin configuration.
Returns the cost_margin_config from litellm_settings.'
operationId: get_cost_margin_config_config_cost_margin_config_get
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
security:
- APIKeyHeader: []
patch:
tags:
- Cost Tracking
summary: Update Cost Margin Config
description: 'Update cost margin configuration.
Updates the cost_margin_config in litellm_settings.
Margins can be:
- Percentage: {"openai": 0.10} = 10% margin
- Fixed amount: {"openai": {"fixed_amount": 0.001}} = $0.001 per request
- Combined: {"vertex_ai": {"percentage": 0.08, "fixed_amount": 0.0005}}
- Global: {"global": 0.05} = 5% global margin on all providers
Example:
```json
{
"global": 0.05,
"openai": 0.10,
"anthropic": {"fixed_amount": 0.001},
"vertex_ai": {"percentage": 0.08, "fixed_amount": 0.0005}
}
```'
operationId: update_cost_margin_config_config_cost_margin_config_patch
requestBody:
content:
application/json:
schema:
additionalProperties:
anyOf:
- type: number
- additionalProperties:
type: number
type: object
type: object
title: Cost Margin Config
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
/config/block_requests_for_models_without_pricing:
get:
tags:
- Cost Tracking
summary: Get Block Requests For Models Without Pricing
operationId: get_block_requests_for_models_without_pricing_config_block_requests_for_models_without_pricing_get
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/BlockUnpricedModelsResponse'
security:
- APIKeyHeader: []
patch:
tags:
- Cost Tracking
summary: Update Block Requests For Models Without Pricing
operationId: update_block_requests_for_models_without_pricing_config_block_requests_for_models_without_pricing_patch
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BlockUnpricedModelsRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/BlockUnpricedModelsResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
/cost/estimate:
post:
tags:
- Cost Tracking
summary: Estimate Cost
description: 'Estimate cost for a given model and token counts.
This endpoint uses the same cost calculation logic as actual requests,
including any configured margins and discounts.
Parameters:
- model: Model name (e.g., "gpt-4", "claude-3-opus")
- input_tokens: Expected input tokens per request
- output_tokens: Expected output tokens per request
- cache_read_input_tokens: Cache-read tokens per request, counted within input_tokens (optional)
- cache_creation_input_tokens: Cache-write tokens per request, counted within input_tokens (optional)
- reasoning_tokens: Reasoning tokens per request, counted within output_tokens (optional)
- num_requests_per_day: Number of requests per day (optional)
- num_requests_per_month: Number of requests per month (optional)
Returns cost breakdown including:
- Per-request costs (input, output, margin, plus the cache-read, cache-write and reasoning shares)
- Daily costs (if num_requests_per_day provided)
- Monthly costs (if num_requests_per_month provided)
Example:
```json
{
"model": "gpt-4",
"input_tokens": 1000,
"cache_read_input_tokens": 800,
"output_tokens": 500,
"reasoning_tokens": 200,
"num_requests_per_day": 100,
"num_requests_per_month": 3000
}
```'
operationId: estimate_cost_cost_estimate_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CostEstimateRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/CostEstimateResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
components:
schemas:
JsonValue: {}
CachePredictionRequest:
properties:
current_deployment_id:
type: string
maxLength: 256
minLength: 1
title: Current Deployment Id
candidate_deployment_id:
type: string
maxLength: 256
minLength: 1
title: Candidate Deployment Id
request:
additionalProperties:
$ref: '#/components/schemas/JsonValue'
type: object
title: Request
additionalProperties: false
type: object
required:
- current_deployment_id
- candidate_deployment_id
- request
title: CachePredictionRequest
CacheTokenBuckets:
properties:
uncached_input_tokens:
type: integer
minimum: 0.0
title: Uncached Input Tokens
default: 0
cache_read_input_tokens:
type: integer
minimum: 0.0
title: Cache Read Input Tokens
default: 0
cache_creation_5m_input_tokens:
type: integer
minimum: 0.0
title: Cache Creation 5M Input Tokens
default: 0
cache_creation_1h_input_tokens:
type: integer
minimum: 0.0
title: Cache Creation 1H Input Tokens
default: 0
additionalProperties: false
type: object
title: CacheTokenBuckets
CachePredictionResponse:
properties:
stay:
$ref: '#/components/schemas/CachePredictionArm'
switch:
$ref: '#/components/schemas/CachePredictionArm'
switch_delta:
anyOf:
- type: number
- type: 'null'
title: Switch Delta
cache_rebuild_penalty:
anyOf:
- type: number
- type: 'null'
title: Cache Rebuild Penalty
pricing_basis:
type: string
const: input_before_discounts_and_margins
title: Pricing Basis
default: input_before_discounts_and_margins
cache_guarantee:
type: boolean
const: false
title: Cache Guarantee
default: false
type: object
required:
- stay
- switch
- switch_delta
- cache_rebuild_penalty
title: CachePredictionResponse
CostEstimateResponse:
properties:
model:
type: string
title: Model
input_tokens:
type: integer
title: Input Tokens
output_tokens:
type: integer
title: Output Tokens
cache_read_input_tokens:
type: integer
title: Cache Read Input Tokens
default: 0
cache_creation_input_tokens:
type: integer
title: Cache Creation Input Tokens
default: 0
reasoning_tokens:
type: integer
title: Reasoning Tokens
default: 0
num_requests_per_day:
anyOf:
- type: integer
- type: 'null'
title: Num Requests Per Day
num_requests_per_month:
anyOf:
- type: integer
- type: 'null'
title: Num Requests Per Month
cost_per_request:
type: number
title: Cost Per Request
description: Total cost per request (includes margin)
input_cost_per_request:
type: number
title: Input Cost Per Request
description: Input token cost per request (before margin)
output_cost_per_request:
type: number
title: Output Cost Per Request
description: Output token cost per request (before margin)
margin_cost_per_request:
type: number
title: Margin Cost Per Request
description: Margin/fee added per request
default: 0.0
cache_read_cost_per_request:
type: number
title: Cache Read Cost Per Request
description: Cache-read share of input_cost_per_request
default: 0.0
cache_creation_cost_per_request:
type: number
title: Cache Creation Cost Per Request
description: Cache-write share of input_cost_per_request
default: 0.0
reasoning_cost_per_request:
type: number
title: Reasoning Cost Per Request
description: Reasoning share of output_cost_per_request
default: 0.0
daily_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Cost
description: Total daily cost (includes margin)
daily_input_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Input Cost
description: Daily input token cost
daily_output_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Output Cost
description: Daily output token cost
daily_margin_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Margin Cost
description: Daily margin/fee
daily_cache_read_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Cache Read Cost
description: Cache-read share of daily_input_cost
daily_cache_creation_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Cache Creation Cost
description: Cache-write share of daily_input_cost
daily_reasoning_cost:
anyOf:
- type: number
- type: 'null'
title: Daily Reasoning Cost
description: Reasoning share of daily_output_cost
monthly_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Cost
description: Total monthly cost (includes margin)
monthly_input_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Input Cost
description: Monthly input token cost
monthly_output_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Output Cost
description: Monthly output token cost
monthly_margin_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Margin Cost
description: Monthly margin/fee
monthly_cache_read_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Cache Read Cost
description: Cache-read share of monthly_input_cost
monthly_cache_creation_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Cache Creation Cost
description: Cache-write share of monthly_input_cost
monthly_reasoning_cost:
anyOf:
- type: number
- type: 'null'
title: Monthly Reasoning Cost
description: Reasoning share of monthly_output_cost
input_cost_per_token:
anyOf:
- type: number
- type: 'null'
title: Input Cost Per Token
description: Rate billed per input token
output_cost_per_token:
anyOf:
- type: number
- type: 'null'
title: Output Cost Per Token
description: Rate billed per output token
cache_read_input_token_cost:
anyOf:
- type: number
- type: 'null'
title: Cache Read Input Token Cost
description: Rate billed per cache-read token
cache_creation_input_token_cost:
anyOf:
- type: number
- type: 'null'
title: Cache Creation Input Token Cost
description: Rate billed per cache-write token
output_cost_per_reasoning_token:
anyOf:
- type: number
- type: 'null'
title: Output Cost Per Reasoning Token
description: Rate billed per reasoning token
provider:
anyOf:
- type: string
- type: 'null'
title: Provider
type: object
required:
- model
- input_tokens
- output_tokens
- cost_per_request
- input_cost_per_request
- output_cost_per_request
title: CostEstimateResponse
description: Response body for /cost/estimate endpoint.
CachePredictionArm:
properties:
deployment_id:
type: string
title: Deployment Id
model:
anyOf:
- type: string
- type: 'null'
title: Model
cache_state:
type: string
enum:
- warm
- partial
- stale
- unknown
- disabled
title: Cache State
default: unknown
reason:
anyOf:
- type: string
- type: 'null'
title: Reason
estimate:
anyOf:
- $ref: '#/components/schemas/CacheCostScenario'
- type: 'null'
cold:
anyOf:
- $ref: '#/components/schemas/CacheCostScenario'
- type: 'null'
warm:
anyOf:
- $ref: '#/components/schemas/CacheCostScenario'
- type: 'null'
evidence:
anyOf:
- $ref: '#/components/schemas/CacheEvidence'
- type: 'null'
token_count_source:
anyOf:
- type: string
const: anthropic_count_tokens
- type: 'null'
title: Token Count Source
type: object
required:
- deployment_id
title: CachePredictionArm
CostEstimateRequest:
properties:
model:
type: string
title: Model
description: Model name (from /model_group/info)
input_tokens:
type: integer
minimum: 0.0
title: Input Tokens
description: Expected input tokens per request
output_tokens:
type: integer
minimum: 0.0
title: Output Tokens
description: Expected output tokens per request
cache_read_input_tokens:
type: integer
minimum: 0.0
title: Cache Read Input Tokens
description: Input tokens read from the prompt cache; counted within input_tokens
default: 0
cache_creation_input_tokens:
type: integer
minimum: 0.0
title: Cache Creation Input Tokens
description: Input tokens written to the prompt cache; counted within input_tokens
default: 0
reasoning_tokens:
type: integer
minimum: 0.0
title: Reasoning Tokens
description: Reasoning tokens the model emits; counted within output_tokens
default: 0
num_requests_per_day:
anyOf:
- type: integer
minimum: 0.0
- type: 'null'
title: Num Requests Per Day
description: Number of requests per day
num_requests_per_month:
anyOf:
- type: integer
minimum: 0.0
- type: 'null'
title: Num Requests Per Month
description: Number of requests per month
type: object
required:
- model
- input_tokens
- output_tokens
title: CostEstimateRequest
description: Request body for /cost/estimate endpoint.
CacheCostScenario:
properties:
tokens:
$ref: '#/components/schemas/CacheTokenBuckets'
input_cost:
type: number
title: Input Cost
type: object
required:
- tokens
- input_cost
title: CacheCostScenario
CacheEvidence:
properties:
observed_at:
type: number
title: Observed At
expires_at:
type: number
title: Expires At
source:
type: string
const: provider_usage
title: Source
default: provider_usage
confidence:
type: string
const: observed
title: Confidence
default: observed
type: object
required:
- observed_at
- expires_at
title: CacheEvidence
BlockUnpricedModelsRequest:
properties:
enabled:
type: boolean
title: Enabled
type: object
required:
- enabled
title: BlockUnpricedModelsRequest
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
BlockUnpricedModelsResponse:
properties:
enabled:
type: boolean
title: Enabled
type: object
required:
- enabled
title: BlockUnpricedModelsResponse
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
APIKeyHeader:
type: apiKey
description: Bearer token
in: header
name: x-litellm-api-key
HTTPBearer:
type: http
scheme: bearer
x-provenance:
method: harvested
publisher: APIClaw
source: https://apiclaw.biz/openapi.json
note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
stamped by stamp-openapi-provenance.py (roadmap#793)