Create a chat completion

An LLM model answers an OpenAI Chat Completions body.

POST /v1/chat/completions

cURL

glm-5.3-flash, streamed live

curl --request POST \ --url https://api.abstract.inc/v1/chat/completions \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model": "glm-5.3-flash", "stream": true, "messages": [ { "role": "user", "content": "Write a haiku about a robot arm." } ] } '

200

{
  "id": "gen-3f9a1c2b7d4e",
  "object": "chat.completion",
  "created": 1790000000,
  "model": "glm-5.3-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A robot arm folds a towel."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 650,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens": 30,
    "total_tokens": 680
  }
}

It returns the answer in the HTTP response, or as server-sent events with stream: true. For robot action models, use get_action.

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

Idempotency-Key · string

The same POST with the same key returns the same answer and never starts a second job. 1 to 200 characters from A-Z a-z 0-9 _ . / : -.

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

Body

application/json

model · enum<string> · required

Available options: kimi-k3.1-pro, glm-5.3, glm-5.3-flash, deepseek-v4.1-flash

messages · object[] · required

role is system, developer, user or assistant. content is a string or an array of text parts; a user message can also carry image_url parts, each a base64 data: URL.

Minimum array length: 1

max_completion_tokens · integer · default: 65536

Counts the model's reasoning as well as its answer.

Required range: 1 <= x <= 65536

max_tokens · integer

The same as max_completion_tokens.

Required range: 1 <= x <= 65536

stream · boolean · default: false

Live server-sent events.

stream_options · object

Accepted. Usage always arrives in its own chunk before data: [DONE].

response_format · object

text, json_object, or json_schema with a named json_schema object.

reasoning_effort · string

temperature · number

top_p · number

user · string

metadata · object

Show child attributes

prompt_cache_key · string

n · integer

store · boolean

Response

200

application/json

The LLM 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