Preview the impact of ZDR on the available endpoints
curl --request GET \
--url https://nemonist.com/api/v1/endpoints/zdr \
--header 'Authorization: Bearer <token>'import requests
url = "https://nemonist.com/api/v1/endpoints/zdr"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://nemonist.com/api/v1/endpoints/zdr', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"data": [
{
"context_length": 8192,
"latency_last_30m": {
"p50": 0.25,
"p75": 0.35,
"p90": 0.48,
"p99": 0.85
},
"max_completion_tokens": 4096,
"max_prompt_tokens": 8192,
"model_id": "openai/gpt-4",
"model_name": "GPT-4",
"name": "OpenAI: GPT-4",
"native_tools": {},
"pricing": {
"completion": "0.00006",
"image": "0",
"prompt": "0.00003",
"request": "0"
},
"provider_name": "OpenAI",
"quantization": "fp16",
"safety_retention": false,
"status": 0,
"supported_parameters": [
"temperature",
"top_p",
"max_tokens"
],
"supports_diarization": false,
"supports_image_reference": false,
"supports_implicit_caching": true,
"supports_multiple_audio_references": false,
"supports_voice_cloning": false,
"tag": "openai",
"throughput_last_30m": {
"p50": 45.2,
"p75": 38.5,
"p90": 28.3,
"p99": 15.1
},
"uptime_last_1d": 99.8,
"uptime_last_30m": 99.5,
"uptime_last_5m": 100
}
]
}{
"error": {
"message": "<string>",
"code": 123,
"type": "<string>"
}
}{
"error": {
"code": 403,
"message": "Only management keys can perform this operation"
}
}{
"error": {
"code": 500,
"message": "Internal Server Error"
}
}{
"error": {
"code": 500,
"message": "Internal Server Error"
}
}{
"error": {
"code": 503,
"message": "Service temporarily unavailable"
}
}Endpoints
Preview the impact of ZDR on the available endpoints
Lists the model endpoints whose providers keep no prompt or completion data (zero data retention).
GET
/
endpoints
/
zdr
Preview the impact of ZDR on the available endpoints
curl --request GET \
--url https://nemonist.com/api/v1/endpoints/zdr \
--header 'Authorization: Bearer <token>'import requests
url = "https://nemonist.com/api/v1/endpoints/zdr"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://nemonist.com/api/v1/endpoints/zdr', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"data": [
{
"context_length": 8192,
"latency_last_30m": {
"p50": 0.25,
"p75": 0.35,
"p90": 0.48,
"p99": 0.85
},
"max_completion_tokens": 4096,
"max_prompt_tokens": 8192,
"model_id": "openai/gpt-4",
"model_name": "GPT-4",
"name": "OpenAI: GPT-4",
"native_tools": {},
"pricing": {
"completion": "0.00006",
"image": "0",
"prompt": "0.00003",
"request": "0"
},
"provider_name": "OpenAI",
"quantization": "fp16",
"safety_retention": false,
"status": 0,
"supported_parameters": [
"temperature",
"top_p",
"max_tokens"
],
"supports_diarization": false,
"supports_image_reference": false,
"supports_implicit_caching": true,
"supports_multiple_audio_references": false,
"supports_voice_cloning": false,
"tag": "openai",
"throughput_last_30m": {
"p50": 45.2,
"p75": 38.5,
"p90": 28.3,
"p99": 15.1
},
"uptime_last_1d": 99.8,
"uptime_last_30m": 99.5,
"uptime_last_5m": 100
}
]
}{
"error": {
"message": "<string>",
"code": 123,
"type": "<string>"
}
}{
"error": {
"code": 403,
"message": "Only management keys can perform this operation"
}
}{
"error": {
"code": 500,
"message": "Internal Server Error"
}
}{
"error": {
"code": 500,
"message": "Internal Server Error"
}
}{
"error": {
"code": 503,
"message": "Service temporarily unavailable"
}
}