Create completion
curl --request POST \
--url https://api.horay.ai/v1/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "<s>[INST] What is the capital of Germany? [/INST]",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"max_tokens": 123,
"stop": [
"<string>"
],
"temperature": 123,
"top_p": 123,
"top_k": 123,
"repetition_penalty": 123,
"stream": true,
"n": 64,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {
"105": 21.4,
"1024": -10.5
},
"seed": 42
}
'import requests
url = "https://api.horay.ai/v1/completions"
payload = {
"prompt": "<s>[INST] What is the capital of Germany? [/INST]",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"max_tokens": 123,
"stop": ["<string>"],
"temperature": 123,
"top_p": 123,
"top_k": 123,
"repetition_penalty": 123,
"stream": True,
"n": 64,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {
"105": 21.4,
"1024": -10.5
},
"seed": 42
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: '<s>[INST] What is the capital of Germany? [/INST]',
model: 'meta-llama/Meta-Llama-3.1-8B-Instruct',
max_tokens: 123,
stop: ['<string>'],
temperature: 123,
top_p: 123,
top_k: 123,
repetition_penalty: 123,
stream: true,
n: 64,
presence_penalty: 123,
frequency_penalty: 123,
logit_bias: {'105': 21.4, '1024': -10.5},
seed: 42
})
};
fetch('https://api.horay.ai/v1/completions', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.horay.ai/v1/completions",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'prompt' => '<s>[INST] What is the capital of Germany? [/INST]',
'model' => 'meta-llama/Meta-Llama-3.1-8B-Instruct',
'max_tokens' => 123,
'stop' => [
'<string>'
],
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'repetition_penalty' => 123,
'stream' => true,
'n' => 64,
'presence_penalty' => 123,
'frequency_penalty' => 123,
'logit_bias' => [
'105' => 21.4,
'1024' => -10.5
],
'seed' => 42
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.horay.ai/v1/completions"
payload := strings.NewReader("{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.horay.ai/v1/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.horay.ai/v1/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"choices": [
{
"text": "<string>",
"finish_reason": "stop",
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
},
"created": 123,
"model": "<string>",
"object": "text_completion",
"prompt": [
{
"text": "<s>[INST] What is the capital of France? [/INST]",
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
]
}
}
]
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}Completions
Create completion
Query a language, code, or image model.
POST
/
completions
Create completion
curl --request POST \
--url https://api.horay.ai/v1/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "<s>[INST] What is the capital of Germany? [/INST]",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"max_tokens": 123,
"stop": [
"<string>"
],
"temperature": 123,
"top_p": 123,
"top_k": 123,
"repetition_penalty": 123,
"stream": true,
"n": 64,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {
"105": 21.4,
"1024": -10.5
},
"seed": 42
}
'import requests
url = "https://api.horay.ai/v1/completions"
payload = {
"prompt": "<s>[INST] What is the capital of Germany? [/INST]",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"max_tokens": 123,
"stop": ["<string>"],
"temperature": 123,
"top_p": 123,
"top_k": 123,
"repetition_penalty": 123,
"stream": True,
"n": 64,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {
"105": 21.4,
"1024": -10.5
},
"seed": 42
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: '<s>[INST] What is the capital of Germany? [/INST]',
model: 'meta-llama/Meta-Llama-3.1-8B-Instruct',
max_tokens: 123,
stop: ['<string>'],
temperature: 123,
top_p: 123,
top_k: 123,
repetition_penalty: 123,
stream: true,
n: 64,
presence_penalty: 123,
frequency_penalty: 123,
logit_bias: {'105': 21.4, '1024': -10.5},
seed: 42
})
};
fetch('https://api.horay.ai/v1/completions', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.horay.ai/v1/completions",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'prompt' => '<s>[INST] What is the capital of Germany? [/INST]',
'model' => 'meta-llama/Meta-Llama-3.1-8B-Instruct',
'max_tokens' => 123,
'stop' => [
'<string>'
],
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'repetition_penalty' => 123,
'stream' => true,
'n' => 64,
'presence_penalty' => 123,
'frequency_penalty' => 123,
'logit_bias' => [
'105' => 21.4,
'1024' => -10.5
],
'seed' => 42
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.horay.ai/v1/completions"
payload := strings.NewReader("{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.horay.ai/v1/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.horay.ai/v1/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"<s>[INST] What is the capital of Germany? [/INST]\",\n \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n \"max_tokens\": 123,\n \"stop\": [\n \"<string>\"\n ],\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"repetition_penalty\": 123,\n \"stream\": true,\n \"n\": 64,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {\n \"105\": 21.4,\n \"1024\": -10.5\n },\n \"seed\": 42\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"choices": [
{
"text": "<string>",
"finish_reason": "stop",
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
},
"created": 123,
"model": "<string>",
"object": "text_completion",
"prompt": [
{
"text": "<s>[INST] What is the capital of France? [/INST]",
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
]
}
}
]
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": null,
"code": null
}
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
A string providing context for the model to complete.
Example:
"<s>[INST] What is the capital of Germany? [/INST]"
The name of the model to query See all of Horay.ai's chat models
Available options:
meta-llama/Meta-Llama-3.1-405B-Instruct, meta-llama/Meta-Llama-3.1-70B-Instruct, meta-llama/Meta-Llama-3.1-8B-Instruct, meta-llama/Llama-3.2-1B-Instruct, meta-llama/Llama-3.2-3B-Instruct, nvidia/Llama-3.1-Nemotron-70B-Instruct, google/gemma-2-27b-it, google/gemma-2-9b-it, Qwen/Qwen2.5-72B-Instruct, Qwen/Qwen2.5-Coder-32B-Instruct, Qwen/Qwen2.5-7B-Instruct, Qwen/Qwen2-72B-Instruct, deepseek-ai/DeepSeek-V2.5, Gryphe/MythoMax-L2-13b Example:
"meta-llama/Meta-Llama-3.1-8B-Instruct"
The maximum number of tokens to generate.
A list of string sequences that will truncate (stop) inference text output. For example, "" will stop generation as soon as the model generates the given token.
A decimal number from 0-1 that determines the degree of randomness in the response. A temperature less than 1 favors more correctness and is appropriate for question answering or summarization. A value closer to 1 introduces more randomness in the output.
A percentage (also called the nucleus parameter) that's used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities. It specifies a probability threshold below which all less likely tokens are filtered out. This technique helps maintain diversity and generate more fluent and natural-sounding text.
An integer that's used to limit the number of choices for the next predicted word or token. It specifies the maximum number of tokens to consider at each step, based on their probability of occurrence. This technique helps to speed up the generation process and can improve the quality of the generated text by focusing on the most likely options.
A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition.
If true, stream tokens as Server-Sent Events as the model generates them instead of waiting for the full model response. The stream terminates with data: [DONE]. If false, return a single JSON object containing the results.
The number of completions to generate for each prompt.
Required range:
1 <= x <= 128A number between -2.0 and 2.0 where a positive value increases the likelihood of a model talking about new topics.
A number between -2.0 and 2.0 where a positive value decreases the likelihood of repeating tokens that have already been mentioned.
Adjusts the likelihood of specific tokens appearing in the generated output.
Show child attributes
Show child attributes
Example:
{ "105": 21.4, "1024": -10.5 }
If specified, the system will make its best effort to perform deterministic sampling, so repeated requests with the same seed and parameters should return the same results. Determinism is not guaranteed to be implemented; the system_fingerprint response parameter should be referenced to monitor backend changes.
Example:
42