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

# Limits

> Request, publish, and query limits enforced by the Semantik API.

Every limit on this page is enforced by the broker. Exceeding one returns `400 invalid_request` with a message naming the field, except where the table says the value is clamped.

All string and text limits are measured in **UTF-8 bytes**, not characters. A 64-byte metadata key holds 64 ASCII characters but fewer accented or CJK ones.

## Request bodies

| Endpoint             | Maximum body |
| -------------------- | ------------ |
| `POST /v1/publish`   | 2 MB         |
| `POST /v1/search`    | 1 MB         |
| `POST /v1/subscribe` | 1 MB         |
| `POST /v1/lint`      | 64 KB        |

A body over the cap returns `413`, not `400`.

## Namespace, model, dimensions

These three fields are required on every publish, search, and subscribe. There is no default — see [Namespaces](/semantik/namespaces) for why.

| Field        | Limit                                                             |
| ------------ | ----------------------------------------------------------------- |
| `namespace`  | ≤ 64 bytes, characters `A–Z a–z 0–9 _ -`                          |
| `dimensions` | 1–4096, and must equal the namespace's configured dimension count |
| `model`      | must match the namespace's configured model                       |

## Publish

```json theme={null}
{
  "namespace": "articles",
  "model": "Qwen3-Embedding-4B",
  "dimensions": 1024,
  "items": [{ "text": "GPU shortage delays cluster expansion." }],
  "metadata": { "source": "internal-feed" },
  "idempotency_key": "feed-2026-08-28-0417"
}
```

| Field             | Limit                                                            |
| ----------------- | ---------------------------------------------------------------- |
| `items`           | exactly 1                                                        |
| `items[].text`    | ≤ 32 KB                                                          |
| `items[].vector`  | ≤ 4096 floats, length must equal `dimensions`, no `NaN` or `Inf` |
| `metadata`        | ≤ 16 keys                                                        |
| `metadata` key    | ≤ 64 bytes                                                       |
| `metadata` value  | ≤ 256 bytes                                                      |
| `metadata` total  | ≤ 4 KB, summed across all keys and values                        |
| `idempotency_key` | ≤ 256 bytes                                                      |

The 32 KB `text` cap applies even when you supply your own `vector`. Text is stored and returned by search whether or not the broker embedded it.

Metadata keys and values, and the idempotency key, must be valid UTF-8 with no control characters. Control bytes are rejected because metadata is echoed back in search results.

## Query

These apply to the SemQL query in `/v1/search`, `/v1/subscribe`, and `/v1/lint`.

Search and subscribe reject a query that exceeds one of them while it is being parsed — before any anchor is embedded, so a rejected query costs no embedding tokens. Lint reports the same problems as diagnostics with `"valid": false` and a `200`, so it is the cheapest way to check a generated query against these caps before sending it.

| Limit                                                        | Value |
| ------------------------------------------------------------ | ----- |
| Anchors per query, across all clauses                        | 32    |
| Anchors in one list (`DIRECTION` toward, `ATTRACT`, `REPEL`) | 8     |
| Namespace names in `NAMESPACE`                               | 8     |
| Namespace names in the `NOT` exclusion list                  | 8     |
| Floats in one vector anchor                                  | 4096  |
| Floats across all vector anchors in a query                  | 8192  |
| Anchor text plus namespace names, combined                   | 4 KB  |
| Nodes per query — clauses plus boolean operators             | 64    |
| Operands per `AND` or `OR`                                   | 16    |
| Parenthesis nesting depth                                    | 128   |

### Value ranges

| Parameter | Range             |
| --------- | ----------------- |
| `WITHIN`  | 0.0–1.0           |
| `CONE`    | 0–π radians       |
| `LIMIT`   | positive integer  |
| `WINDOW`  | positive duration |

`WITHIN` and `TOP` are mutually exclusive on a single clause.

## Result count

`LIMIT` is the one query value that is clamped rather than rejected.

| Source                | Behaviour                             |
| --------------------- | ------------------------------------- |
| `limit` request field | wins over the query's `LIMIT` clause  |
| `LIMIT` in the query  | used when the request field is absent |
| neither set           | 100 results                           |
| either set above 1000 | clamped to 1000                       |

<Warning>
  A request for `LIMIT 50000` succeeds and returns at most 1000 results. Because the response is a success, a client that assumes it received everything will silently miss results. Page with a narrower `WINDOW` or a tighter query rather than a larger `LIMIT`.
</Warning>

## Working within the limits

**Anchor lists overflow before anchor counts do.** A `DIRECTION` list built by expanding synonyms hits the 8-item cap long before the query hits 32 anchors. Split into two clauses joined with `OR` instead of dropping concepts:

```sql theme={null}
MATCH DIRECTION(["outage", "downtime", "degraded", "unavailable"]) CONE 0.4
   OR DIRECTION(["latency spike", "timeout", "slow response"]) CONE 0.4
```

**The 4 KB text budget is shared.** It covers every anchor string and namespace name in one query, so a handful of sentence-length anchors can exhaust it well below 32 anchors. Short concept phrases match as well and cost less of the budget.

**Prefer text anchors to vector anchors.** A single 1024-dimension vector anchor consumes an eighth of the 8192-float query budget, so a query can carry only eight of them. Text anchors have no equivalent per-query ceiling beyond the 4 KB budget.