curl -X POST https://www.token-nova.com/v1/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo-instruct",
"prompt": "把下面一句话改写得更正式：这个接口挺好用。",
"max_tokens": 120,
"temperature": 0.3
}'
{
"id": "cmpl_abc123",
"object": "text_completion",
"created": 1735689600,
"model": "gpt-3.5-turbo-instruct",
"choices": [
{
"index": 0,
"text": "该接口具备良好的易用性。",
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 22,
"completion_tokens": 10,
"total_tokens": 32
}
}
{
"error": {
"message": "field model is required",
"type": "invalid_request_error",
"param": "",
"code": "invalid_request"
}
}
{
"error": {
"message": "Invalid API key provided",
"type": "invalid_request_error",
"param": "",
"code": "invalid_api_key"
}
}
{
"error": {
"message": "User quota insufficient",
"type": "new_api_error",
"param": "",
"code": "insufficient_user_quota"
}
}
{
"error": {
"message": "The current request rate is too high, please try again later",
"type": "new_api_error",
"param": "",
"code": "too_many_requests"
}
}
{
"error": {
"message": "bad response body",
"type": "new_api_error",
"param": "",
"code": "bad_response_body"
}
}
OpenAI Format
Text Completion API
Generate text using the OpenAI Legacy Completions compatible format.
POST
https://www.token-nova.com
/
v1
/
completions
curl -X POST https://www.token-nova.com/v1/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo-instruct",
"prompt": "把下面一句话改写得更正式：这个接口挺好用。",
"max_tokens": 120,
"temperature": 0.3
}'
{
"id": "cmpl_abc123",
"object": "text_completion",
"created": 1735689600,
"model": "gpt-3.5-turbo-instruct",
"choices": [
{
"index": 0,
"text": "该接口具备良好的易用性。",
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 22,
"completion_tokens": 10,
"total_tokens": 32
}
}
{
"error": {
"message": "field model is required",
"type": "invalid_request_error",
"param": "",
"code": "invalid_request"
}
}
{
"error": {
"message": "Invalid API key provided",
"type": "invalid_request_error",
"param": "",
"code": "invalid_api_key"
}
}
{
"error": {
"message": "User quota insufficient",
"type": "new_api_error",
"param": "",
"code": "insufficient_user_quota"
}
}
{
"error": {
"message": "The current request rate is too high, please try again later",
"type": "new_api_error",
"param": "",
"code": "too_many_requests"
}
}
{
"error": {
"message": "bad response body",
"type": "new_api_error",
"param": "",
"code": "bad_response_body"
}
}
Text Completion API
The Legacy Completions API usesprompt as input and is suitable for businesses still using the old OpenAI SDK or simple text completion workflows. For new conversational scenarios, it is recommended to use the chat completions API.
Request Body
string
required
Model name.
string | array<string>
required
Input prompt.
boolean
Whether to enable streaming output.
integer
Maximum number of tokens to generate.
number
Sampling temperature.
number
Nucleus sampling parameter.
string | array<string>
Stop sequences.
Request Example
curl -X POST https://www.token-nova.com/v1/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo-instruct",
"prompt": "把下面一句话改写得更正式：这个接口挺好用。",
"max_tokens": 120,
"temperature": 0.3
}'
Response Example
{
"id": "cmpl_abc123",
"object": "text_completion",
"created": 1735689600,
"model": "gpt-3.5-turbo-instruct",
"choices": [
{
"index": 0,
"text": "该接口具备良好的易用性。",
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 22,
"completion_tokens": 10,
"total_tokens": 32
}
}
{
"error": {
"message": "field model is required",
"type": "invalid_request_error",
"param": "",
"code": "invalid_request"
}
}
{
"error": {
"message": "Invalid API key provided",
"type": "invalid_request_error",
"param": "",
"code": "invalid_api_key"
}
}
{
"error": {
"message": "User quota insufficient",
"type": "new_api_error",
"param": "",
"code": "insufficient_user_quota"
}
}
{
"error": {
"message": "The current request rate is too high, please try again later",
"type": "new_api_error",
"param": "",
"code": "too_many_requests"
}
}
{
"error": {
"message": "bad response body",
"type": "new_api_error",
"param": "",
"code": "bad_response_body"
}
}