Get Completion Job Result
Return the answer of an ended job, with the status that POST /v1/completions gave it: 200 and the Completion, or the error object with its own status, such as 429 budget_exceeded or 502. A cancelled job answers 409 job_cancelled, and a job that the server failed to run answers 500 job_failed. While the job is queued or running, 202 with the job and Retry-After: 1. 30 days after the job ended, 410 job_result_expired.
bearerAuthorizationBearer <token>An API key: Authorization: Bearer sk-acs-..., or a key of the old platform, acs-bm-.... A User makes and revokes keys in the App.
job_id*string^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|[fF]{8}-[fF]{4}-[fF]{4}-[fF]{4}-[fF]{12})$uuidThe completion succeeded.
application/json- response
The completion succeeded.
id*stringobject*"text_completion""text_completion"created*integermodel*stringchoices*array<>usage*activations?|nullcurl -X GET 'https://api.v2.infra.acsresearch.org/v1/completion-jobs/497f6eca-6276-4993-bfeb-53cbbbba6f08/result' \ -H 'Authorization: Bearer <API_KEY>'{ "id": "string", "object": "text_completion", "created": 0, "model": "string", "choices": [ { "index": 0, "text": "string", "logprobs": { "text_offset": [ 0 ], "token_logprobs": [ 0 ], "tokens": [ "string" ], "top_logprobs": [ { "property1": 0, "property2": 0 } ] }, "finish_reason": "string", "stop_reason": "string", "prompt_logprobs": [ { "property1": { "logprob": 0, "rank": 0, "decoded_token": "string" }, "property2": { "logprob": 0, "rank": 0, "decoded_token": "string" } } ] } ], "usage": { "prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0 }, "activations": { "residual_stream": { "data": "string", "dtype": "string", "original_dtype": "string", "shape": [ 0 ], "compression": "zstd" } }}Get Completion Job GET
Return the job and its status. A 200 here does not mean that the completion succeeded: read GET /v1/completion-jobs/{job_id}/result.
Cancel Completion Job POST
Cancel a queued or running job, and answer the job. A running job stops its Inference request. A job that ended stays as it is, and the answer is the same job.