mirror of
https://github.com/netbirdio/netbird.git
synced 2026-09-24 15:49:06 +02:00
Store per-bucket LLM cost, derive totals on read.
This commit is contained in:
braginini
@@ -5839,6 +5839,26 @@ components:
|
||||
format: double
|
||||
description: Estimated USD cost of the request.
|
||||
example: 0.0231
|
||||
input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Cost of the non-cached input tokens. Base component of cost_usd.
|
||||
example: 0.0048
|
||||
cached_input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Cost of the prompt-cache read tokens. Base component of cost_usd, and part of cache_cost_usd.
|
||||
example: 0.0015
|
||||
cache_creation_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Cost of the prompt-cache write tokens. Base component of cost_usd, and part of cache_cost_usd.
|
||||
example: 0.1130
|
||||
output_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Cost of the output tokens. Base component of cost_usd.
|
||||
example: 0.0038
|
||||
cache_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
@@ -5869,6 +5889,10 @@ components:
|
||||
- total_tokens
|
||||
- cached_input_tokens
|
||||
- cache_creation_tokens
|
||||
- input_cost_usd
|
||||
- cached_input_cost_usd
|
||||
- cache_creation_cost_usd
|
||||
- output_cost_usd
|
||||
- cost_usd
|
||||
- cache_cost_usd
|
||||
AgentNetworkAccessLogsResponse:
|
||||
@@ -5961,6 +5985,26 @@ components:
|
||||
format: double
|
||||
description: Total estimated USD cost across the session.
|
||||
example: 0.1617
|
||||
input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of non-cached input tokens across the session.
|
||||
example: 0.0210
|
||||
cached_input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of prompt-cache read tokens across the session.
|
||||
example: 0.0015
|
||||
cache_creation_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of prompt-cache write tokens across the session.
|
||||
example: 0.1130
|
||||
output_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of output tokens across the session.
|
||||
example: 0.0262
|
||||
cache_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
@@ -5994,6 +6038,10 @@ components:
|
||||
- total_tokens
|
||||
- cached_input_tokens
|
||||
- cache_creation_tokens
|
||||
- input_cost_usd
|
||||
- cached_input_cost_usd
|
||||
- cache_creation_cost_usd
|
||||
- output_cost_usd
|
||||
- cost_usd
|
||||
- cache_cost_usd
|
||||
- decision
|
||||
@@ -6061,6 +6109,26 @@ components:
|
||||
format: int64
|
||||
description: Total prompt-cache write tokens in the bucket.
|
||||
example: 45000
|
||||
input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of non-cached input tokens in the bucket.
|
||||
example: 1.12
|
||||
cached_input_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of prompt-cache read tokens in the bucket.
|
||||
example: 0.06
|
||||
cache_creation_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of prompt-cache write tokens in the bucket.
|
||||
example: 0.36
|
||||
output_cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
description: Total cost of output tokens in the bucket.
|
||||
example: 0.77
|
||||
cost_usd:
|
||||
type: number
|
||||
format: double
|
||||
@@ -6078,6 +6146,10 @@ components:
|
||||
- total_tokens
|
||||
- cached_input_tokens
|
||||
- cache_creation_tokens
|
||||
- input_cost_usd
|
||||
- cached_input_cost_usd
|
||||
- cache_creation_cost_usd
|
||||
- output_cost_usd
|
||||
- cost_usd
|
||||
- cache_cost_usd
|
||||
AgentNetworkSettings:
|
||||
|
||||
@@ -1735,9 +1735,15 @@ type AgentNetworkAccessLog struct {
|
||||
// CacheCostUsd Portion of cost_usd billed for prompt-cache usage.
|
||||
CacheCostUsd float64 `json:"cache_cost_usd"`
|
||||
|
||||
// CacheCreationCostUsd Cost of the prompt-cache write tokens. Base component of cost_usd, and part of cache_cost_usd.
|
||||
CacheCreationCostUsd float64 `json:"cache_creation_cost_usd"`
|
||||
|
||||
// CacheCreationTokens Input tokens written to the provider's prompt cache. Zero for providers without a cache-write bucket.
|
||||
CacheCreationTokens int64 `json:"cache_creation_tokens"`
|
||||
|
||||
// CachedInputCostUsd Cost of the prompt-cache read tokens. Base component of cost_usd, and part of cache_cost_usd.
|
||||
CachedInputCostUsd float64 `json:"cached_input_cost_usd"`
|
||||
|
||||
// CachedInputTokens Input tokens read from the provider's prompt cache. Additive to input_tokens for Anthropic-shape providers; a subset of input_tokens for OpenAI.
|
||||
CachedInputTokens int64 `json:"cached_input_tokens"`
|
||||
|
||||
@@ -1762,6 +1768,9 @@ type AgentNetworkAccessLog struct {
|
||||
// Id Unique identifier for the access log entry.
|
||||
Id string `json:"id"`
|
||||
|
||||
// InputCostUsd Cost of the non-cached input tokens. Base component of cost_usd.
|
||||
InputCostUsd float64 `json:"input_cost_usd"`
|
||||
|
||||
// InputTokens Input (prompt) tokens consumed.
|
||||
InputTokens int64 `json:"input_tokens"`
|
||||
|
||||
@@ -1771,6 +1780,9 @@ type AgentNetworkAccessLog struct {
|
||||
// Model Requested LLM model.
|
||||
Model *string `json:"model,omitempty"`
|
||||
|
||||
// OutputCostUsd Cost of the output tokens. Base component of cost_usd.
|
||||
OutputCostUsd float64 `json:"output_cost_usd"`
|
||||
|
||||
// OutputTokens Output (completion) tokens produced.
|
||||
OutputTokens int64 `json:"output_tokens"`
|
||||
|
||||
@@ -1822,9 +1834,15 @@ type AgentNetworkAccessLogSession struct {
|
||||
// CacheCostUsd Portion of cost_usd billed for prompt-cache usage across the session.
|
||||
CacheCostUsd float64 `json:"cache_cost_usd"`
|
||||
|
||||
// CacheCreationCostUsd Total cost of prompt-cache write tokens across the session.
|
||||
CacheCreationCostUsd float64 `json:"cache_creation_cost_usd"`
|
||||
|
||||
// CacheCreationTokens Total prompt-cache write tokens across the session.
|
||||
CacheCreationTokens int64 `json:"cache_creation_tokens"`
|
||||
|
||||
// CachedInputCostUsd Total cost of prompt-cache read tokens across the session.
|
||||
CachedInputCostUsd float64 `json:"cached_input_cost_usd"`
|
||||
|
||||
// CachedInputTokens Total prompt-cache read tokens across the session.
|
||||
CachedInputTokens int64 `json:"cached_input_tokens"`
|
||||
|
||||
@@ -1843,12 +1861,18 @@ type AgentNetworkAccessLogSession struct {
|
||||
// GroupIds Union of the authorising group ids across the session's entries.
|
||||
GroupIds *[]string `json:"group_ids,omitempty"`
|
||||
|
||||
// InputCostUsd Total cost of non-cached input tokens across the session.
|
||||
InputCostUsd float64 `json:"input_cost_usd"`
|
||||
|
||||
// InputTokens Total input (prompt) tokens across the session.
|
||||
InputTokens int64 `json:"input_tokens"`
|
||||
|
||||
// Models Distinct models seen in the session.
|
||||
Models *[]string `json:"models,omitempty"`
|
||||
|
||||
// OutputCostUsd Total cost of output tokens across the session.
|
||||
OutputCostUsd float64 `json:"output_cost_usd"`
|
||||
|
||||
// OutputTokens Total output (completion) tokens across the session.
|
||||
OutputTokens int64 `json:"output_tokens"`
|
||||
|
||||
@@ -2368,18 +2392,30 @@ type AgentNetworkUsageBucket struct {
|
||||
// CacheCostUsd Portion of cost_usd billed for prompt-cache usage in the bucket.
|
||||
CacheCostUsd float64 `json:"cache_cost_usd"`
|
||||
|
||||
// CacheCreationCostUsd Total cost of prompt-cache write tokens in the bucket.
|
||||
CacheCreationCostUsd float64 `json:"cache_creation_cost_usd"`
|
||||
|
||||
// CacheCreationTokens Total prompt-cache write tokens in the bucket.
|
||||
CacheCreationTokens int64 `json:"cache_creation_tokens"`
|
||||
|
||||
// CachedInputCostUsd Total cost of prompt-cache read tokens in the bucket.
|
||||
CachedInputCostUsd float64 `json:"cached_input_cost_usd"`
|
||||
|
||||
// CachedInputTokens Total prompt-cache read tokens in the bucket.
|
||||
CachedInputTokens int64 `json:"cached_input_tokens"`
|
||||
|
||||
// CostUsd Total estimated USD spend in the bucket.
|
||||
CostUsd float64 `json:"cost_usd"`
|
||||
|
||||
// InputCostUsd Total cost of non-cached input tokens in the bucket.
|
||||
InputCostUsd float64 `json:"input_cost_usd"`
|
||||
|
||||
// InputTokens Total input (prompt) tokens in the bucket.
|
||||
InputTokens int64 `json:"input_tokens"`
|
||||
|
||||
// OutputCostUsd Total cost of output tokens in the bucket.
|
||||
OutputCostUsd float64 `json:"output_cost_usd"`
|
||||
|
||||
// OutputTokens Total output (completion) tokens in the bucket.
|
||||
OutputTokens int64 `json:"output_tokens"`
|
||||
|
||||
|
||||
Reference in New Issue
Block a user