# LLMSTATS.GET

> Read the running totals and the last-minute window of an LLM usage stats bucket.

URL: https://docs.hotkv.com/commands/llmstats-get/

```
LLMSTATS.GET name
```

- Group: LLM usage and budgets
- Complexity: O(1)
- HotKV Cloud: Performance and Scale plans
- On-Premise: requires the llm-stats license feature

LLM usage stats keep running totals of the requests, tokens, cost and latency of your model calls in named buckets, for example one per tenant or per model. `LLMSTATS.GET` returns a bucket's totals since it was created or
last reset, plus the requests, tokens and cost of the last minute. For a
bucket that does not exist, every field is zero.

## Return value

The reply is a flat array of alternating field names and values in both RESP2 and RESP3 (it is not sent as a RESP3 map). The fields, in order:

| Field | Type | Meaning |
| --- | --- | --- |
| `requests` | Integer | Requests recorded. |
| `errors` | Integer | Requests recorded with `ERROR 1`. |
| `input_tokens` | Integer | Uncached input tokens. |
| `output_tokens` | Integer | Output tokens. |
| `cached_tokens` | Integer | Cache-read tokens. |
| `cost_usd` | Bulk string | Total cost in US dollars. |
| `avg_latency_ms` | Bulk string | Mean latency in milliseconds. |
| `requests_1m` | Integer | Requests in the last minute. |
| `tokens_1m` | Integer | All tokens (input, output, cache read and cache write) in the last minute. |
| `cost_usd_1m` | Bulk string | Cost in the last minute, in US dollars. |
| `cache_write_5m_tokens` | Integer | Tokens written to 5-minute provider caches. |
| `cache_write_1h_tokens` | Integer | Tokens written to 1-hour provider caches. |
| `unpriced_requests` | Integer | Requests recorded with a `MODEL` that has no price. |

Errors:

- `ERR wrong number of arguments for 'llmstats.get' command` if the argument count is wrong.
- `NOLICENSE llm-stats requires a HotKV license. Contact sales@hotkv.com` if your license does not include the `llm-stats` feature.

## Examples

```
127.0.0.1:6379> LLMSTATS.RECORD model_sonnet5 100000 2000 50000 0 420 MODEL claude-sonnet-5 CACHEWRITE5M 10000
OK
127.0.0.1:6379> LLMSTATS.GET model_sonnet5
 1) "requests"
 2) (integer) 1
 3) "errors"
 4) (integer) 0
 5) "input_tokens"
 6) (integer) 100000
 7) "output_tokens"
 8) (integer) 2000
 9) "cached_tokens"
10) (integer) 50000
11) "cost_usd"
12) "0.255"
13) "avg_latency_ms"
14) "420"
15) "requests_1m"
16) (integer) 1
17) "tokens_1m"
18) (integer) 162000
19) "cost_usd_1m"
20) "0.255"
21) "cache_write_5m_tokens"
22) (integer) 10000
23) "cache_write_1h_tokens"
24) (integer) 0
25) "unpriced_requests"
26) (integer) 0
```

## Compatibility

HotKV-only command. Redis and Valkey have no equivalent.

## See also

[LLMSTATS.BUCKET](https://docs.hotkv.com/commands/llmstats-bucket/index.md), [LLMSTATS.RECORD](https://docs.hotkv.com/commands/llmstats-record/index.md), [LLMSTATS.RESET](https://docs.hotkv.com/commands/llmstats-reset/index.md), [LLMSTATS.DROP](https://docs.hotkv.com/commands/llmstats-drop/index.md), [LLMSTATS.LIST](https://docs.hotkv.com/commands/llmstats-list/index.md), [LLMSTATS.PRICE](https://docs.hotkv.com/commands/llmstats-price/index.md), [AI features guide](https://docs.hotkv.com/ai-features/index.md)