AI Usage
Cost, latency, tokens and errors across the ModelGateway.
Calls
49
Total cost
$0.041333
Tokens
10,007
Avg latency
2261 ms
Errors
0
Model comparison
| Model | Calls | Cost | Tokens | Avg latency | Error rate |
|---|---|---|---|---|---|
| anthropic/claude-haiku-4-5 | 17 | $0.007497 | 4,797 | 1892 ms | 0% |
| openai/text-embedding-3-small | 13 | $0.000001 | 143 | 1321 ms | 0% |
| anthropic/claude-sonnet-4-6 | 11 | $0.01353 | 3,234 | 3149 ms | 0% |
| anthropic/claude-opus-4-8 | 8 | $0.020305 | 1,833 | 3353 ms | 0% |
Cost per task
| Task | Calls | Cost | Tokens | Avg latency |
|---|---|---|---|---|
| response_generation | 8 | $0.020305 | 1,833 | 3353 ms |
| human_handoff_detection | 8 | $0.009894 | 2,226 | 3486 ms |
| response_validation | 5 | $0.004058 | 2,330 | 2016 ms |
| rag_relevance_ranking | 3 | $0.003636 | 1,008 | 2252 ms |
| intent_classification | 8 | $0.002664 | 2,048 | 2259 ms |
| rag_query_rewrite | 4 | $0.000775 | 419 | 1005 ms |
| embeddings | 13 | $0.000001 | 143 | 1321 ms |
Cost per tenant
| Tenant | Calls | Cost | Tokens | Avg latency |
|---|---|---|---|---|
| 00000000… | 40 | $0.041333 | 9,958 | 2458 ms |
| a3fb472b… | 9 | $0.0000 | 49 | 1388 ms |
Top conversations by cost
| Conversation | Calls | Cost | Tokens |
|---|---|---|---|
| 33333333… | 12 | $0.013843 | 3,625 |
| — | 24 | $0.010956 | 2,678 |
| 11111111… | 6 | $0.007351 | 1,847 |
| 44444444… | 4 | $0.005805 | 1,219 |
| 55555555… | 3 | $0.003378 | 638 |
Errors by model
| Model | Errors | Last error |
|---|---|---|
| No errors in this window 🎉 | ||