Cost & Usage
Track current spend pacing, provider mix, and the execution history behind paid runtime work without juggling a second budgeting model.
Month
Spend
$0.00
Metered runtime spend for the current month
Derived
Daily Budget
$0.00
Calculated from the monthly cap
Remaining
Monthly Headroom
$0.00
Spend left before the monthly cap
Providers
Active Mix
5
Claude Code + OpenAI Codex App Server + Anthropic Direct API + OpenAI Direct API + Ollama
Pricing
Freshness
Stale
Updated Mar 16, 2026, 5:00 PM
Budget pacing is on track
Spend is within the configured pacing windows. Derived daily caps continue to roll forward from the monthly budget.
Primary spend driver
OpenAI Direct API represents 79% of filtered spend.
$20.00 of Unlimited
Monthly reset Aug 1, 2026, 12:00 AM.
Official provider pricing with manual refresh and the last known update time.
anthropic
Updated Mar 16, 2026, 5:00 PM
Claude Opus
Input / output
$5.00 / 1M
$25.00 / 1M
Claude Sonnet
Input / output
$3.00 / 1M
$15.00 / 1M
Claude Haiku
Input / output
$1.00 / 1M
$5.00 / 1M
Claude Pro
Monthly plan
$20.00
Claude Max 5x
Monthly plan
$100
Claude Max 20x
Monthly plan
$200
openai
Updated Mar 16, 2026, 5:00 PM
Codex Mini
Input / output
$1.50 / 1M
$6.00 / 1M
GPT-5
Input / output
$10.00 / 1M
$30.00 / 1M
GPT-4o
Input / output
$2.50 / 1M
$10.00 / 1M
Spend Trends
Spend velocity
7-day and 30-day spend series
7-day
30-day
Activity tokens
Secondary telemetry for the same window
7-day
30-day
Provider Breakdown
OpenAI Direct API
openai79% of filtered spend across 2 runs
Spend
$1.55
Tokens
64.8K
Claude Code
anthropicPlan priced19% of filtered spend across 3 runs
Spend
$0.365
Tokens
35.4K
Anthropic Direct API
anthropic3% of filtered spend across 1 runs
Spend
$0.052
Tokens
6.4K
Ollama
local0% of filtered spend across 1 runs
Spend
$0.00
Tokens
3.1K
Model Breakdown
Spend-first concentration by model for last 30 days.
gpt-5
OpenAI Direct APIopenai • 1 run • 52.2K tokens
Spend
$1.48
Tokens
52.2K
claude-sonnet-4
Claude Codeanthropic • 3 runs • 35.4K tokens
Spend
$0.365
Tokens
35.4K
gpt-5-mini
OpenAI Direct APIopenai • 1 run • 12.6K tokens
Spend
$0.074
Tokens
12.6K
claude-3-5-sonnet
Anthropic Direct APIanthropic • 1 run • 6.4K tokens
Spend
$0.052
Tokens
6.4K
llama3.1:8b
Ollamalocal • 1 run • 3.1K tokens
Spend
$0.00
Tokens
3.1K
Audit Log
Filtered execution history for last 30 days.
| Timestamp | Activity | Linked entity | Runtime | Cost | Tokens | Status |
|---|---|---|---|---|---|---|
| Jan 28, 58514, 12:53 AM | Workflow step claude-3-5-sonnet | Anthropic Direct API anthropic | ≥$0.052 | 6.4K | BlockedPartial usage | |
| Jan 28, 58514, 12:53 AM | Workflow step claude-sonnet-4 | Claude Code anthropic • plan priced | ≥$0.186 | 18.4K | CompletedPartial usage | |
| Jan 28, 58514, 12:53 AM | Workflow step claude-sonnet-4 | Claude Code anthropic • plan priced | ≥$0.091 | 9.2K | CompletedPartial usage | |
| Jan 28, 58514, 12:53 AM | Workflow step claude-sonnet-4 | Claude Code anthropic • plan priced | ≥$0.088 | 7.8K | CompletedPartial usage | |
| Jan 28, 58514, 12:53 AM | Task run llama3.1:8b | Ollama local | ≥$0.00 | 3.1K | CompletedPartial usage | |
| Jan 28, 58514, 12:53 AM | Workflow step gpt-5-mini | OpenAI Direct API openai | ≥$0.074 | 12.6K | CompletedPartial usage | |
| Jan 28, 58514, 12:53 AM | Workflow step gpt-5 | OpenAI Direct API openai | ≥$1.48 | 52.2K | FailedPartial usage |