POST

/v1/complete

Generate code or text completions from a prompt in a single request.

POST https://api.nascentist.ai/v1/complete

Request

Name	Type	Required	Default	Description
prompt	string	Yes	—	The code or text to complete. Include surrounding context for best results.
model	string	No	nascentist-1	Model ID to use.
max_tokens	integer	No	500	Max tokens to generate. Range: 1–8000 (plan-dependent).
temperature	float	No	0.2	Sampling temperature. 0 = deterministic, 1 = creative. For code, 0.1–0.3 is recommended.
stop	string[]	No	null	Up to 4 stop sequences.
stream	boolean	No	false	If true, returns an SSE stream.
language	string	No	null	Language hint for better results: "python", "javascript", "typescript", "go", "rust", "java", "cpp".
system	string	No	null	System-level instruction prepended to the prompt.

Request Examples

9 lines

curl -X POST https://api.nascentist.ai/v1/complete \
  -H "Authorization: Bearer nsc_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "def binary_search(arr, target):",
    "max_tokens": 300,
    "temperature": 0.1,
    "language": "python"
  }'

Response

14 lines

{
  "id": "cmpl_01ABC123def456",
  "object": "completion",
  "model": "nascentist-1",
  "content": "    left, right = 0, len(arr) - 1\n    while left <= right:\n        mid = (left + right) // 2\n        if arr[mid] == target:\n            return mid\n        elif arr[mid] < target:\n            left = mid + 1\n        else:\n            right = mid - 1\n    return -1",
  "finish_reason": "stop",
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 68,
    "total_tokens": 82
  },
  "latency_ms": 734,
  "created_at": "2026-03-01T04:18:00Z"
}

Field	Description
id	Unique completion identifier.
object	Response object type.
content	Generated completion text.
finish_reason	Why generation stopped (stop, length, etc.).
usage	Prompt/completion/total token usage.
latency_ms	Server-side response latency in milliseconds.

Streaming

Set stream: true to receive Server-Sent Events chunks. Each chunk includes incremental text in delta.

5 lines

data: {"delta": "    left, "}

data: {"delta": "right = 0, "}

data: [DONE]

Errors

Common completion errors

Use the Error Reference for all error objects. Common errors here are authentication_error, invalid_request_error, and rate_limit_error.