Chat Completions

POST /v1/chat/completions

Creates a chat completion. This is the primary endpoint for generating AI responses.

Request

Headers

Header	Required	Description
x-api-key	Yes	Your API key
Content-Type	Yes	application/json

Body Parameters

Parameter	Type	Required	Description
model	string	Yes	Model ID to use (see Models)
messages	array	Yes	List of messages in the conversation
temperature	float	No	Sampling temperature, 0.0 to 2.0
max_tokens	integer	No	Maximum tokens to generate
top_p	float	No	Nucleus sampling parameter, 0.0 to 1.0
stream	boolean	No	Not yet implemented — coming in v2.0. Stream the response via Server-Sent Events (default: false)
stop	string or array	No	Stop sequence(s) to end generation

Message Object

Field	Type	Required	Description
role	string	Yes	One of system, user, or assistant
content	string	Yes	The message content

Response

Non-Streaming

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "claude-3-7-sonnet",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  }
}

Streaming

Not yet implemented. Streaming support (stream: true) is coming in v2.0. Requests with stream: true will return an error.

Finish Reasons

Value	Meaning
stop	Natural end of response or stop sequence hit
length	Hit max_tokens limit
content_filter	Content was filtered by the provider's safety system

Examples

Basic Completion

curl -X POST https://api.consus.io/v1/chat/completions \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-7-sonnet",
    "messages": [
      {"role": "user", "content": "What is FedRAMP?"}
    ]
  }'

With System Prompt and Parameters

curl -X POST https://api.consus.io/v1/chat/completions \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-4-5-sonnet",
    "messages": [
      {"role": "system", "content": "You are a helpful government compliance assistant."},
      {"role": "user", "content": "Summarize CMMC Level 2 requirements."}
    ],
    "temperature": 0.3,
    "max_tokens": 2048
  }'

Multi-Turn Conversation

curl -X POST https://api.consus.io/v1/chat/completions \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-7-sonnet",
    "messages": [
      {"role": "user", "content": "What is an ATO?"},
      {"role": "assistant", "content": "An ATO (Authority to Operate) is a formal authorization..."},
      {"role": "user", "content": "How long does it typically take to get one?"}
    ]
  }'

Streaming

Not yet implemented. Streaming support is coming in v2.0.