Chat Completions

POST /v1/chat/completions — Create a compressed chat completion.

Endpoint

POST https://www.opencompress.ai/api/v1/chat/completions

Headers

Header	Required	Description
Authorization	Yes	Bearer sk-occ-your-key-here
Content-Type	Yes	application/json

Request body

model · string · required

Model identifier. See Supported Models for the full list.

Examples: gpt-4o, claude-sonnet-4-6, gemini-2.5-pro

messages · array · required

Array of message objects. Each message has a role and content.

Supported roles: system, user, assistant

stream · boolean · default: "false"

If true, returns a stream of server-sent events.

temperature · number

Sampling temperature (0-2). Passed through to the model.

max_tokens · integer

Maximum tokens to generate. Passed through to the model.

top_p · number

Nucleus sampling parameter. Passed through to the model.

stop · string | array

Stop sequences. Passed through to the model.

All standard OpenAI parameters (frequency_penalty, presence_penalty, logprobs, tools, tool_choice, etc.) are passed through to the upstream model.

Response

id · string

Unique identifier for this completion.

object · string

Always "chat.completion".

created · integer

Unix timestamp of when the completion was created.

model · string

The model used, matching your request.

choices · array

Array of completion choices.

Show Choice object

index · integer

Index of this choice.

message · object

The assistant’s message with role and content.

finish_reason · string

Why generation stopped: "stop", "length", "tool_calls".

usage · object

Token usage statistics.

Show Usage object

prompt_tokens · integer

Number of tokens in the compressed prompt.

completion_tokens · integer

Number of tokens in the response.

total_tokens · integer

Total tokens (prompt + completion).

Example

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="sk-occ-your-key-here",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a concise technical writer."},
        {"role": "user", "content": "Explain how JWT authentication works."},
    ],
    temperature=0.7,
    max_tokens=500,
)

print(response.choices[0].message.content)