Retrieve a chat completion

Returns an LLM completion your account created. A completion from a retired model reads back from its kept answer.

GET /v1/chat/completions/{completion_id}

Retrieve a chat completion

cURL

curl --request GET \
  --url https://api.abstract.inc/v1/chat/completions/{completion_id} \
  --header 'Authorization: Bearer <token>'

200

{
  "id": "resp_abc123",
  "object": "chat.completion",
  "created": 1790000000,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "RFC 8628 defines the OAuth 2.0 device authorization grant."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens": 96,
    "total_tokens": 110
  }
}

Authorizations

Authorization · string · header · required

Your Abstract API key. Get it with abstract login, pass it as $(abstract token).

Headers

Abstract-Version · enum<string>

The API version your client was written for. 2026-10-27 is the only version. Without this header the request is answered under the newest version; a version the API does not answer is refused with 400 unsupported_api_version before anything runs.

Available options: 2026-10-27

Path Parameters

completion_id · string · required

The id from the POST answer.

Pattern: ^[A-Za-z0-9_-]{1,200}$

Response

200

application/json

The finished chat completion.

id · string · required

object · string · required

Allowed value: "chat.completion"

created · integer · required

Unix seconds.

model · string · required

choices · object[] · required

Show child attributes

usage · object · required

Show child attributes