> ## Documentation Index
> Fetch the complete documentation index at: https://docs.overshoot.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Prompt cache and threads

> Reuse cached prompt prefixes across related chat completion requests.

Use the same `thread_id` for related requests in the same user conversation and model to improve prompt-cache reuse when available.

```json theme={null}
{
  "model": "google/gemma-4-26B-A4B-it",
  "thread_id": "session-123",
  "messages": [{ "role": "user", "content": "Continue from our previous context." }]
}
```

Cache observability is returned under `overshoot.cache`:

```json theme={null}
{
  "overshoot": {
    "cache": {
      "thread_id": "session-123",
      "cache_hit": true,
      "cached_input_tokens": 5000
    }
  }
}
```

* `thread_id` is the ID you supplied, or `null` when none was provided.
* `cache_hit` is true when cached prompt tokens were reported.
* `cached_input_tokens` is the number of prompt tokens served from prefix cache.

<Note>
  Cache metadata is observability only. It is not a guarantee that future requests will receive a cache hit.
</Note>