Create Completion (OpenAI Completions API Compatible) | Caesar

OpenAI Completions API compatible endpoint. Creates a research job and returns the result in OpenAI text completion format. Supports both streaming and non-streaming responses.

Note: This endpoint does not support file attachments. Files are only supported on /compat/chat/completions. To include files in your research, use the Chat Completions endpoint with multimodal content parts.

OpenAI Completions API compatible endpoint. Creates a research job and returns the result in OpenAI text completion format. Supports both streaming and non-streaming responses. **Note:** This endpoint does not support file attachments. Files are only supported on `/compat/chat/completions`. To include files in your research, use the Chat Completions endpoint with multimodal content parts.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

modelstringRequired

Model identifier (accepted for compatibility).

promptstringRequired

The prompt to generate completions for.

max_tokensintegerOptional>=1

Maximum number of tokens to generate (accepted for compatibility).

temperaturedoubleOptional0-2Defaults to 1

Sampling temperature (accepted for compatibility).

top_pdoubleOptional0-1Defaults to 1

Nucleus sampling parameter (accepted for compatibility).

stopstring or list of stringsOptional

Sequences where the API will stop generating (accepted for compatibility).

seedintegerOptional

Random seed for deterministic sampling (accepted for compatibility).

streambooleanOptionalDefaults to false

Whether to stream partial progress via SSE.

stream_optionsobjectOptional

metadataobjectOptional

Research configuration parameters. When not provided, auto mode is used to determine optimal settings.

Response

Completion response (or SSE stream if stream=true).

idstring

Unique identifier for the completion.

objectenum

Object type.

Allowed values:

createdinteger

Unix timestamp of when the completion was created.

modelstring

Model used for the completion.

choiceslist of objects

List of completion choices.

usageobject

1	import requests
2
3	url = "https://api.caesar.xyz/compat/completions"
4
5	payload = { "body": {
6	"model": "caesar-research",
7	"prompt": "What are the latest breakthroughs in quantum computing and their potential applications?",
8	"max_tokens": 150,
9	"temperature": 0.7,
10	"top_p": 0.9,
11	"stop": ["
12	", "###"],
13	"seed": 42,
14	"stream": False,
15	"metadata": {
16	"reasoning_loops": 4,
17	"source_timeout": 30,
18	"reasoning_mode": True,
19	"allow_early_exit": True,
20	"exclude_social": False,
21	"system_prompt": "You are a research assistant synthesizing recent scientific papers."
22	}
23	} }
24	headers = {
25	"Authorization": "Bearer <token>",
26	"Content-Type": "application/json"
27	}
28
29	response = requests.post(url, json=payload, headers=headers)
30
31	print(response.json())

1	{
2	"id": "9c6f8b1a-2a4f-4a35-86b9-0d0b5e25d5e5",
3	"object": "text_completion",
4	"created": 1700000000,
5	"model": "caesar-research",
6	"choices": [
7	{
8	"text": "Quantum computing has seen significant advances in error correction and qubit coherence times, enabling more stable and scalable quantum processors. Recent breakthroughs include the development of quantum algorithms for optimization and simulation, which have potential applications in cryptography, drug discovery, and materials science.",
9	"index": 0,
10	"finish_reason": "stop"
11	}
12	],
13	"usage": {
14	"prompt_tokens": 25,
15	"completion_tokens": 120,
16	"total_tokens": 145
17	}
18	}

Authentication

Request

Response

Errors