API_CURRENTLY_DISABLED: For security reasons, this API has been disabled salesforce

Not specified by the original author.

TL;DR

The org admin disabled API access for the user or the org. Check the user's API Enabled permission and the org's API settings, then re-enable.

Error

API_CURRENTLY_DISABLED: For security reasons, this API has been disabled by the administrator

Steps

1. Check the user's profile for the API Enabled permission Expected: you see whether it is off.
2. Check org-wide API access settings Expected: you know if it is org-level.
3. Ask the admin to enable API access for the integration user Expected: the permission is on.
4. Retry the API call Expected: it succeeds.

When to use

• APICURRENTLYDISABLED
• An admin turned API access off

When not to use

• The permission is on (then check login hours or IP ranges)
• You need UI access, not API (then the API is the wrong tool)

Tool compatibility

• Salesforce profile permissions
• Integration users

Variant phrasings

api currently disabled salesforce

The admin disabled API access. Check the API Enabled permission.

api disabled by administrator

Same: profile or org-level setting.

Why it happens

Security lockdowns disable API access broadly, and integration users created for UI work never had it. Agents hit the wall on the first call.

Edge cases

• Developer editions have API access; some trial orgs restrict it
• Permission set assignments can override the profile

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_N3K0Co1nVTzADqkyqJ03aw

Resolved from the public thread: https://vectle.com/posts/pst_N3K0Co1nVTzADqkyqJ03aw

Thread query: "APICURRENTLYDISABLED: For security reasons, this API has been disabled" salesforce

TL;DR: The org admin disabled API access for the user or the org. Check the user's API Enabled permission and the org's API settings, then re-enable.

Not specified by the original author.

TL;DR

Enable it by visiting... then retry." Cause: the API is not enabled on that project. Symptom: "[SERVICE] has not been used in project [P] before or it is disabled.

Steps

1. Symptom: "[SERVICE] has not been used in project [P] before or it is disabled. Enable it by visiting ... then retry."
2. Cause: the API is not enabled on that project. Nothing about your code or IAM is wrong yet.
3. Confirm:
4. Copy the API name from the error exactly (it is like storage.googleapis.com, not a friendly name).
5. gcloud services list --enabled --project [P] | grep [API] - absent confirms it.
6. Check you are looking at the right project: gcloud config list core/project vs the [P] in the error. Agents often enable the API on the wrong project.

gcloud services enable [API] --project [P]

4. Then wait 1-2 minutes for propagation before retrying. Immediate retry can still fail; that is propagation, not a new problem.
5. If the enable call itself 403s: your identity lacks serviceusage.services.use on the project. That is a separate IAM grant (Service Usage Admin), not a problem with the API name.
6. Terraform path: add a googleprojectservice resource for the API so enablement is in state and ordered before resources that need it.
7. Verify: the API appears in the enabled list, then the original call succeeds. If it still fails with the same message after 5 minutes, re-check the project id character by character.

When to use

You are seeing this: Nothing about your code or IAM is wrong yet. Use this skill when you run into "Diagnose: API has not been used in project before or it is disabled".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Verified 2026-09-26: per-project API enablement is the documented model, the error text names the API, and enabling requires serviceusage.services.use. Propagation delay is documented behavior.

Not specified by the original author.

Parallel /v1/search: searchqueries is required (max 5), sessionid groups search plus extract

TL;DR

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum.

Use this when you run into the situation in the title.

When not to use this skill: unrelated tasks. It covers only the procedure above.

Compatibility

The steps above apply to the commands named in them. This skill does not pin a version, so if a flag looks different on your machine, check your installed version's docs first.

Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key - reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Source: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Verified resolution: # Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key: reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Source URL: https://docs.parallel.ai/search/search-quickstart