# Trigger an on-demand self-tuning optimize

`POST /contexts/{slug}/optimize`

:::code-group
```bash title="cURL"
curl --request POST \
  --url https://{host}/api/contexts/{slug}/optimize \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "eval_pass_rate_threshold": 123,
  "retrieval_p90_latency_ms": 123,
  "optimize_timeout_seconds": 123,
  "max_iterations": 123,
  "max_tool_turns": 123,
  "models": [
    "<string>"
  ],
  "candidate_queries": [
    {
      "ask": "<string>",
      "answer": "<string>",
      "fallback_to_chunks": true,
      "latency_ms": 123
    }
  ],
  "pinecone_api_key": "<string>"
}'
```

```json title="200"
{
  "task_id": "<string>",
  "state": "<string>",
  "exploring": true,
  "profiling": true,
  "importing": true
}
```
:::

## Authorizations

- `Authorization` (header, string, required) — Bearer authentication header of the form `Bearer <token>`.

## Path Parameters

- `slug` (path, string, required) — Context slug or UUID.

## Headers

- `X-Pinecone-Api-Version` (header, string) — Date-based contract version, echoed back on the same header. Omit for the default (`2026-07`); send `unstable` for the in-development surface. An unrecognized value is rejected with `400 unsupported_api_version`.

## Body

- `eval_pass_rate_threshold` (body, number) — Pass rate a candidate manifest must clear to count as ready.
- `retrieval_p90_latency_ms` (body, integer) — The p90 latency bar a candidate must stay under.
- `optimize_timeout_seconds` (body, integer) — Default 7200
- `max_iterations` (body, integer) — Default 20
- `max_tool_turns` (body, integer) — Default 200
- `models` (body, string\[]) — Model-id overrides passed to the optimize runtime
- `candidate_queries` (body, object\[]) — Recent query records to tune toward (absent = no-op)
- `pinecone_api_key` (body, string) — Task-token override; normally not needed

## Response

- `200` — Optimize enqueued (`state: optimizing`)
- `404` — Not found
- `409` — Context is already optimizing or was never curated

## Related pages

- [List contexts (newest first, with stats)](./data-plane-contexts-list-contexts-newest-first-with-stats.md)
- [Create a context](./data-plane-contexts-create-a-context.md)
- [Get a context](./data-plane-contexts-get-a-context.md)
- [Update a context](./data-plane-contexts-update-a-context.md)
- [Delete a context (and its Pinecone indexes)](./data-plane-contexts-delete-a-context-and-its-pinecone-indexes.md)
- [Per-context task statistics](./data-plane-contexts-per-context-task-statistics.md)
- [Run the Design-flow explore agent (propose a manifest)](./data-plane-contexts-run-the-design-flow-explore-agent-propose-a-manifest.md)
- [Estimate the token + time cost of curating the in-progress manifest](./data-plane-contexts-estimate-the-token-time-cost-of-curating-the-in-progress-manifest.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.