curl -X POST "https://t.ato2.nodesms.com/v1/completions" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "string",
"prompt": "string"
}'
import openai
client = openai.OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.completions.create(
model="string",
prompt="string"
)
print(response.choices[0].text)
{
"id": "string",
"object": "text_completion",
"created": 0,
"model": "string",
"choices": [
{
"text": "string",
"index": 0,
"finish_reason": "string"
}
],
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"completion_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0
}
}
}
Text Completions
Create a text completion based on a given prompt. This is the legacy Completions endpoint, suitable for scenarios where you need the model to continue or complete text.
POST
/
v1
/
completions
curl -X POST "https://t.ato2.nodesms.com/v1/completions" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "string",
"prompt": "string"
}'
import openai
client = openai.OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.completions.create(
model="string",
prompt="string"
)
print(response.choices[0].text)
{
"id": "string",
"object": "text_completion",
"created": 0,
"model": "string",
"choices": [
{
"text": "string",
"index": 0,
"finish_reason": "string"
}
],
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"completion_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0
}
}
}
Headers
string
required
Bearer token authentication. Format:
Authorization: Bearer sk-xxxxxxBody
Format:application/json
string
required
Model ID
string | string[]
required
Prompt text, can be a string or an array of strings
integer
Maximum number of tokens to generate
number
Sampling temperature
number
Nucleus sampling parameter
integer
Number of completions to generate
boolean
Whether to stream the response
string | string[]
Stop sequence(s)
string
Suffix text for insertion
boolean
Whether to echo the prompt text in the output
Response
200 Successfully created response
Format:application/json
TypeScript type definitions
TypeScript type definitions
interface CompletionResponse {
id?: string;
object?: string;
created?: number;
model?: string;
choices?: {
text?: string;
index?: number;
finish_reason?: string;
}[];
usage?: {
prompt_tokens?: number;
completion_tokens?: number;
total_tokens?: number;
prompt_tokens_details?: {
cached_tokens?: number;
text_tokens?: number;
audio_tokens?: number;
image_tokens?: number;
};
completion_tokens_details?: {
text_tokens?: number;
audio_tokens?: number;
reasoning_tokens?: number;
};
};
}
string
Completion ID
string
Object type, value is
text_completioninteger
Creation timestamp
string
Model ID
object[]
object
Token usage information
Show Properties
Show Properties
integer
Prompt token count
integer
Completion token count
integer
Total token count
object
curl -X POST "https://t.ato2.nodesms.com/v1/completions" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "string",
"prompt": "string"
}'
import openai
client = openai.OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.completions.create(
model="string",
prompt="string"
)
print(response.choices[0].text)
{
"id": "string",
"object": "text_completion",
"created": 0,
"model": "string",
"choices": [
{
"text": "string",
"index": 0,
"finish_reason": "string"
}
],
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"completion_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0
}
}
}
Last modified on October 28, 2026
Was this page helpful?