LLM call recording
Trace every LLM call across 9 providers — cost, latency, and errors, one by one.
Setup is one line pasted into your coding agent, or one line of SDK.
Recent calls (example)
Click a row to expand
| Time | Model | Cost | Latency | Status |
|---|---|---|---|---|
| 14:32:18 | gpt-5.5 | <$0.01 | 1.14 s | ● Success |
| 14:32:09 | claude-sonnet-5 | <$0.01 | 892 ms | ● Success |
| 14:31:54 | gemini-3.5-flash | — | 322 ms | ● Error |
| 14:31:42 | gpt-5.6-luna | <$0.01 | 412 ms | ● Success |
| 14:30:51 | mistral-medium-latest | <$0.01 | 716 ms | ● Success |
Prompt
Reply politely and concisely to a customer who says they cannot log in.
Completion
Sure, let me check the situation. Could you try resetting your password from the link below?
9 providers supported
Wrap the OpenAI / Anthropic / Gemini / Mistral SDK clients — Grok, Kimi, DeepSeek, Qwen, and Muse Spark work through the OpenAI-compatible API. Argosvix records the rest automatically.
Per-call detail you can trace
Token counts, USD cost, latency, and errors — per call, in one view. Full prompt/completion storage is an opt-in Pro+ option (all supported providers).
Cost (USD)
$0.0049
Total tokens
1,763
Input
1,590
Output
173
Cache hit
32%
Latency
3963 ms
Status
success
Error
—
Full prompt/response storage is a Pro+ opt-in.
Dashboard, MCP & REST
Reach the same data from the web UI, from Claude Desktop / Cursor / Codex CLI, or from curl.