Skip to main content
POST
cURL
Unlike chat completions, the prompt string is handed to the model as-is, no chat template, no roles, no system prompt. The model simply continues your text. Streaming works the same way as on the chat endpoint.
The models in the catalog are instruction-tuned, and their quality comes from their chat formatting, prefer chat completions for anything conversational, and keep this endpoint for continuation-style tasks or legacy integrations that require the prompt/text shape.

Authorizations

Authorization
string
header
required

Bearer followed by an inference API key (sk-prl-infapi-). Create keys on the API Keys page. Management keys (sk-prl-mgmt-) cannot call models.

Body

application/json
model
string
required

A catalog model ID from GET /models.

prompt
string
required

Raw text the model continues.

max_tokens
integer

Cap on generated tokens.

temperature
number

Sampling parameter; behaves as on chat completions.

top_p
number

Sampling parameter; behaves as on chat completions.

frequency_penalty
number

Sampling parameter; behaves as on chat completions.

presence_penalty
number

Sampling parameter; behaves as on chat completions.

stop
string[]

Sampling parameter; behaves as on chat completions.

seed
integer

Sampling parameter; behaves as on chat completions.

top_k
integer

Sampling parameter extension; behaves as on chat completions.

min_p
number

Sampling parameter extension; behaves as on chat completions.

n
integer
default:1

Number of choices to generate, 1 to 8. Defaults to 1.

Required range: 1 <= x <= 8
stream
boolean

Server-sent events with choices[0].text deltas, terminated by data: [DONE].

Response

The completion, or an event stream when streaming.

id
string

Completion ID.

object
enum<string>

Always text_completion.

Available options:
text_completion
created
integer

Unix timestamp (seconds).

model
string

The model that served the request.

choices
object[]
usage
object

prompt_tokens, completion_tokens, total_tokens, what you're billed on.