Skip to main content
ThinkFeel supports an OpenAI-compatible text completions endpoint at /api/v1/completions. OpenAI SDKs for Completions, including AI SDK, can point their base URL to https://playground.curvelabs.org/api/v1. 
POST https://playground.curvelabs.org/api/v1/completions
This is different from the ThinkFeel SDK and CLI base URL setting, which should use only the site origin. Send either prompt or messages, not both. model must be your persona ID.

​
Headers

HeaderTypeRequiredDescription
Content-TypestringYesMust be application/json
AuthorizationstringConditionalOpenAI-style bearer API key for API-key billing
x-api-keystringConditionalAlternative to Authorization; one key header is required for API-key billing

​
Body parameters

ParameterTypeRequiredDescription
modelstringYesPersona ID UUID only
messagesarrayConditionalMulti-turn text messages; accepts user, assistant, system, and developer roles with string or text-part array content
promptstring or string arrayConditionalText prompt, as a string or one-item array, when messages is omitted
nnumberNoNumber of completions, 1-5. Defaults to 1
echobooleanNoPrepend the prompt to the output text
stopstring or string arrayNoStop sequence or sequences

​
Compatibility notes

  • Provide either prompt or messages.
  • When using messages, include the full conversation history and ensure the last role is user.
  • messages supports user, assistant, system, and developer roles.
  • model must be your persona ID UUID provided during onboarding.
  • prompt must be a string or a single-element array.
  • n is capped at 5.
  • Message content can be a plain string or an array of text parts.
  • Optional timestamp, createdAt, and created_at values are accepted and normalized when present.
  • Streaming is not supported on this V1 endpoint. stream: true returns an error.
  • max_tokens and logprobs are rejected.
  • Other OpenAI parameters are accepted but ignored: temperature, top_p, presence_penalty, frequency_penalty, best_of, seed, suffix, and user.
  • Output text is normalized, stop sequences are applied, and echo prepends the prompt.
  • Responses omit usage.

​
Request

curl -X POST https://playground.curvelabs.org/api/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY_HERE" \
  -d '{
    "model": "YOUR_PERSONA_ID",
    "prompt": "hey, how's your day?",
    "n": 1,
    "echo": false,
    "stop": ["\n\n"]
  }'

​
Response

{
  "id": "cmpl-...",
  "object": "text_completion",
  "created": 1737656583,
  "model": "YOUR_PERSONA_ID",
  "choices": [
    {
      "text": "pretty chill so far, you?",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "chunks": ["pretty chill so far, you?"]
    }
  ]
}