Developer Tool · Analytics
Token & Savings Analytics
Understand exactly which models, routing paths, and endpoints drive your cost-avoided savings — broken down over the last 30 days.
Total Tokens (30d)
39.7M
across all models
Total Saved (30d)
$5,788
vs. cloud-only
Avg. Cost Reduction
73%
vs. hyperscaler baseline
Top Model by Savings
Phi-3.5-mini
$1,826 saved
Token Consumption by Model — 30-day
Daily tokens generated, stacked by model
- Llama-3.2-1B
- Phi-3.5-mini
- Qwen-2.5-7B
- Llama-3.3-70B
Token Volume by Routing Path — 30-day
Daily tokens split across local, mesh, and cloud routes
- Local
- Mesh
- Cloud
Top Performing Models
| Model | Requests | Latency (ms) | Cost/Request | Throughput |
|---|---|---|---|---|
| Phi-3.5-mini | 4,029,595 | 178 | $0.0009 | 63.9 tok/s |
| Qwen-2.5-7B | 2,408,209 | 343 | $0.0013 | 75.2 tok/s |
| Llama-3.2-1B | 911,912 | 69 | $0.0010 | 82.1 tok/s |
| Llama-3.3-70B | 790,961 | 189 | $0.0007 | 42.7 tok/s |
Cost-Avoided Savings by Model
Cloud equivalent cost vs. actual MeshInfer cost
1Phi-3.5-mini
Tokens
8.12M
Cloud equiv.
$2,436.39
Actual
$617.88
Saved
$1,818.51
75% off
2Llama-3.3-70B
Tokens
7.66M
Cloud equiv.
$2,299.47
Actual
$640.44
Saved
$1,659.03
72% off
3Llama-3.2-1B
Tokens
5.45M
Cloud equiv.
$1,633.95
Actual
$485.48
Saved
$1,148.47
70% off
4Qwen-2.5-7B
Tokens
3.81M
Cloud equiv.
$1,143.59
Actual
$344.71
Saved
$798.88
70% off
Cost-Avoided Savings by Endpoint
Top endpoints ranked by absolute dollars saved
| Endpoint | Tokens | Savings | % Off Cloud | Impact |
|---|---|---|---|---|
| /v1/ai/embed | 3.12M | $1,027.05 | 36% | #1 |
| /v1/ai/summarize | 2.49M | $740.18 | 72% | #2 |
| /v1/ai/chat | 1.71M | $515.90 | 32% | #3 |
| /v1/ai/translate | 1.70M | $496.02 | 49% | #4 |
| /v1/ai/classify | 1.37M | $472.50 | 61% | #5 |