curl --request POST \
--url https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run"
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, headers=headers)
print(response.text)const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"data": {
"prompt": {
"id": 2048,
"text": "best crm for a startup",
"topic_id": 17,
"last_checked_at": null,
"created_at": "2026-05-12T09:31:00+00:00"
},
"models": [
"chatgpt",
"gemini",
"perplexity"
],
"status": "queued"
},
"meta": {
"project": "64f1a2b3c4d5e6f708192a3b",
"realtime_credits_remaining": 11
},
"credits": {
"charged": 1,
"remaining": 2942
},
"request_id": "req_01j9x503e4f5g6h7i8j9k0l1m2"
}{
"error": {
"code": "UNAUTHENTICATED",
"message": "Missing or invalid API key. Send it as: Authorization: Bearer rk_live_YOUR_KEY"
},
"request_id": "req_01j9x4q7z8y9x0w1v2u3t4s5r6"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "PROJECT_FORBIDDEN",
"message": "This key cannot access that project."
},
"request_id": "req_01j9x4q7z8y9x0w1v2u3t4s5r9"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "RATE_LIMITED",
"message": "Too many requests. Slow down and retry.",
"details": {
"retry_after": 21
}
},
"request_id": "req_01j9x4r2s3t4u5v6w7x8y9z0a1"
}Run a prompt now
Asks every model the project tracks this prompt right away, instead of waiting for the next scheduled run. The run happens in the background and takes a few minutes.
To know when it is done, list prompts and watch the status per model go from pending to processing to completed. Then list responses for the prompt. The new rows have realtime: true.
Cost: 1 API credit plus 1 realtime credit from the project owner’s balance. Nothing is charged when the run is refused.
Limits: 10 per minute per key. One run per prompt at a time.
Needs: Write.
curl --request POST \
--url https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run"
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, headers=headers)
print(response.text)const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.radarkit.ai/v1/projects/{project}/prompts/{prompt}/run', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"data": {
"prompt": {
"id": 2048,
"text": "best crm for a startup",
"topic_id": 17,
"last_checked_at": null,
"created_at": "2026-05-12T09:31:00+00:00"
},
"models": [
"chatgpt",
"gemini",
"perplexity"
],
"status": "queued"
},
"meta": {
"project": "64f1a2b3c4d5e6f708192a3b",
"realtime_credits_remaining": 11
},
"credits": {
"charged": 1,
"remaining": 2942
},
"request_id": "req_01j9x503e4f5g6h7i8j9k0l1m2"
}{
"error": {
"code": "UNAUTHENTICATED",
"message": "Missing or invalid API key. Send it as: Authorization: Bearer rk_live_YOUR_KEY"
},
"request_id": "req_01j9x4q7z8y9x0w1v2u3t4s5r6"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "PROJECT_FORBIDDEN",
"message": "This key cannot access that project."
},
"request_id": "req_01j9x4q7z8y9x0w1v2u3t4s5r9"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "<string>",
"message": "<string>",
"details": {}
},
"request_id": "req_01j9x4m2p7q8r9s0t1u2v3w4x5"
}{
"error": {
"code": "RATE_LIMITED",
"message": "Too many requests. Slow down and retry.",
"details": {
"retry_after": 21
}
},
"request_id": "req_01j9x4r2s3t4u5v6w7x8y9z0a1"
}Authorizations
Your API key. Create one in Settings, API keys. Send it as Authorization: Bearer rk_live_YOUR_KEY.
Path Parameters
The project id. 24 characters. From List projects.
^[0-9a-f]{24}$The prompt id. From List prompts.
Response
The run is queued.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
What this call cost and what is left. Also in the X-RadarKit-Credits-Charged and X-RadarKit-Credits-Remaining headers.
Show child attributes
Show child attributes
A unique id for this call. Also in the X-Request-Id header. Quote it when you contact support.
"req_01j9x4m2p7q8r9s0t1u2v3w4x5"