WorkspaceUsage
Platform usage over the last 7 days. All models are free — we track tokens and quotas, not money.
- Requests
- 8
- Input tokens
- 2,021
- Output tokens
- 4,870
- Avg. latency
- 3.4 s
- Errors
- 9
| Model | Provider | Requests | Tokens (input/output) | Avg. latency |
|---|---|---|---|---|
| Llama 3.3 70B | Groq | 5 | 209 / 1,673 | 1.0 s |
| Gemini 2.5 Flash | Google Gemini | 2 | 1,771 / 2,508 | 10.5 s |
| Llama 3.1 8B | Groq | 1 | 41 / 689 | 1.0 s |