A sample LLMIntel dashboard with a week of realistic traffic across three apps.
You’re viewing demo data — this is what LLMIntel looks like with a week of real traffic. Sign up and your own data appears minutes after your first instrumented call.
| Model | State | Retirement |
|---|---|---|
| meta.llama3-1-405b-instruct-v1:0 | retiring | in 21 days2026-07-25 |
Pricing known for 6 of 6 models you run. Cheapest by input: gpt-5-nano-2025-08-07 at $0.05/1M.
Want cheaper/faster on-par alternatives for these models? See optimization →
Frozen at ingest — priced from the model rates at the time of each call, so past spend never shifts. Window: last 13 months.
Dollars flowing through models that retire within 90 days. Migrate before the provider 4xxs you — see recommended replacements on each model page.
| Model | Retirement | Spend |
|---|---|---|
| meta.llama3-1-405b-instruct-v1:0 | in 21 days2026-07-25 | $212.40 |
Allocated to the API key that reported each call — attribute spend to the app, service, or team behind the key. Follows the environment filter above.
| API key | Requests | Tokens | Spend | Share |
|---|---|---|---|---|
| checkout-assistant (prod) | 261,000 | 58M | $742.11 | 58% |
| support-copilot (prod) | 118,000 | 28M | $389.55 | 30% |
| internal-tools (staging) | 31,000 | 9.2M | $141.20 | 11% |
| Unattributedpre-attribution | 2,000 | 1.2M | $11.20 | 1% |
“Unattributed” is usage recorded before per-key attribution shipped. New calls are tagged with the reporting key automatically.
| Model | Provider | Requests | Input | Output | Spend |
|---|---|---|---|---|---|
| claude-sonnet-4-5-20250929 | Anthropic | 168,400 | 31M | 8.5M | $620.86 |
| gpt-5-2025-08-07 | OpenAI | 96,800 | 22M | 6.9M | $292.40 |
| gpt-5-mini-2025-08-07 | OpenAI | 74,300 | 12M | 3.4M | $32.40 |
| gpt-5-nano-2025-08-07 | OpenAI | 41,900 | 5.6M | 1.5M | $8.00 |
| gpt-4o (2024-08-06) | Azure AI Foundry | 22,600 | 2.9M | 900k | $118.00 |
| meta.llama3-1-405b-instruct-v1:0 | AWS Bedrock | 8,000 | 780k | 220k | $212.40 |