AI 成本中心
按服务商、模型和产品归因 Token 支出，并与产品组合 AI 预算核对。
Demo data· $50.3K / month run-rate
本月至今
$3.4K
+12.1%vs last month run-比率
14.3M requests billed this month
Projected month end
$52.8K
$1.4K of headroom left
Budget utilisation
6.3%
$54.2K budget · 28 days remaining
总计 tokens
41.2B
$1.22 per million tokens
缓存命中 比率
47.1%
14.2B input tokens served from cache
AI 成本 / 收入
11.6%
Gross-margin guardrail: 15%
服务商每日支出
Stacked 服务商 contribution over the 过去 30 天
5 providers
按服务商支出
Share of recomputed 每月 AI budget
按产品支出
Which 产品 consume the inference budget
本月累计趋势
Actual 每日 支出 in the 当前 billing month
模型 ledger
Top models by attributed 成本, latency and cache efficiency
Tool calls
13.9M
Reasoning tokens
3.1B
Output tokens
7.9B
Avg tokens / request
2.9K
Input tokens
30.1B
Recomputed 总计
$50.3K
| Model | Provider | Cost | Share | Requests | Cache hit | P95 latency |
|---|---|---|---|---|---|---|
| gpt-5 | OpenAI | $21.2K | 42.1% | 1.5M | 51.9% | 5.4s |
| gpt-5-mini | OpenAI | $12.5K | 24.8% | 7.7M | 45.5% | 1.8s |
| claude-4.5-sonnet | Anthropic | $7.5K | 15% | 325.7K | 39.1% | 3.8s |
| claude-4.5-opus | Anthropic | $3.6K | 7.3% | 21.9K | 39.4% | 8.2s |
| deepseek-v4 | DeepSeek | $2K | 4% | 2M | 43.4% | 2.9s |
| gemini-3-pro | $1.8K | 3.6% | 278K | 60.6% | 3.5s | |
| gemini-3-flash | $1.1K | 2.3% | 2.1M | 51.7% | 864ms | |
| qwen-3-max | Qwen | $501.88 | 1% | 386.6K | 35.5% | 2.4s |