Skip to main content
POST
/
v1
/
completions
cURL
curl --location --request POST https://api.writer.com/v1/completions \
 --header "Authorization: Bearer <token>" \
 --header "Content-Type: application/json" \
--data-raw '{"model":"palmyra-x-003-instruct","prompt":"Write me a short SEO article about camping gear","max_tokens":150,"temperature":0.7,"top_p":0.9,"stop":["."],"best_of":1,"random_seed":42,"stream":false}'
{
  "choices": [
    {
      "text": "Sure! Here's a search engine optimized article about...",
      "log_probs": null
    }
  ],
  "model": "palmyra-x-003-instruct"
}
Deprecation notice: The following models are deprecated and will be removed on July 13, 2026: palmyra-x-003-instruct, palmyra-vision, palmyra-med, palmyra-fin, and palmyra-creative.Migration path: Use palmyra-x5 as the replacement for all deprecated models. Palmyra X5 supports a 1M-token context window and covers general-purpose, financial, medical, and creative use cases. For vision workloads, use chat with images with Palmyra X5 instead of palmyra-vision. See the deprecation policy for more information.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your Writer API key.

Body

application/json
​
model
string
required

The ID of the model to use for generating text. Supports palmyra-x5, palmyra-x4, palmyra-fin, palmyra-med, palmyra-creative, and palmyra-x-003-instruct.

​
prompt
string
required

The input text that the model will process to generate a response.

​
max_tokens
integer<int64>

The maximum number of tokens that the model can generate in the response.

​
temperature
number<double>

Controls the randomness of the model's outputs. Higher values lead to more random outputs, while lower values make the model more deterministic.

​
top_p
number<double>

Used to control the nucleus sampling, where only the most probable tokens with a cumulative probability of top_p are considered for sampling, providing a way to fine-tune the randomness of predictions.

​
stop

Specifies stopping conditions for the model's output generation. This can be an array of strings or a single string that the model will look for as a signal to stop generating further tokens.

​
best_of
integer<int32>

Specifies the number of completions to generate and return the best one. Useful for generating multiple outputs and choosing the best based on some criteria.

​
random_seed
integer<int32>

A seed used to initialize the random number generator for the model, ensuring reproducibility of the output when the same inputs are provided.

​
stream
boolean

Determines whether the model's output should be streamed. If true, the output is generated and sent incrementally, which can be useful for real-time applications.

Response

Successful response

​
choices
object[]
required

A list of choices generated by the model, each containing the text of the completion and associated metadata such as log probabilities.

Minimum array length: 1
​
model
string

The identifier of the model that was used to generate the responses in the 'choices' array.