curl --request POST \
--url https://flow.seekr.com/v1/inference/chat/completions \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "meta-llama/Llama-3.1-8B-Instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is the capital of France?"
}
],
"max_completion_tokens": 128,
"temperature": 0.7,
"stream": false
}
'import requests
url = "https://flow.seekr.com/v1/inference/chat/completions"
payload = {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is the capital of France?"
}
],
"max_completion_tokens": 128,
"temperature": 0.7,
"stream": False
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'meta-llama/Llama-3.1-8B-Instruct',
messages: [
{role: 'system', content: 'You are a helpful assistant.'},
{role: 'user', content: 'What is the capital of France?'}
],
max_completion_tokens: 128,
temperature: 0.7,
stream: false
})
};
fetch('https://flow.seekr.com/v1/inference/chat/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://flow.seekr.com/v1/inference/chat/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([
'model' => 'meta-llama/Llama-3.1-8B-Instruct',
'messages' => [
[
'role' => 'system',
'content' => 'You are a helpful assistant.'
],
[
'role' => 'user',
'content' => 'What is the capital of France?'
]
],
'max_completion_tokens' => 128,
'temperature' => 0.7,
'stream' => false
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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://flow.seekr.com/v1/inference/chat/completions"
payload := strings.NewReader("{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
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://flow.seekr.com/v1/inference/chat/completions")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://flow.seekr.com/v1/inference/chat/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "<string>",
"content": "<string>",
"refusal": "<string>",
"function_call": {
"name": "<string>",
"arguments": "<string>"
},
"tool_calls": [
{
"id": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
},
"type": "function"
}
],
"reasoning": "<string>"
},
"logprobs": {
"content": [
{
"token": "<string>",
"logprob": -9999,
"bytes": [
123
],
"top_logprobs": [
{
"token": "<string>",
"logprob": -9999,
"bytes": [
123
]
}
]
}
]
},
"finish_reason": "stop",
"stop_reason": 123,
"token_ids": [
123
]
}
],
"usage": {
"prompt_tokens": 0,
"total_tokens": 0,
"completion_tokens": 0,
"prompt_tokens_details": {
"cached_tokens": 123,
"created_cache_tokens": 123,
"multimodal_tokens": {}
}
},
"object": "chat.completion",
"service_tier": "auto",
"system_fingerprint": "<string>",
"prompt_logprobs": [
{}
],
"prompt_token_ids": [
123
],
"prompt_text": "<string>",
"metrics": {
"time_to_first_token_ms": 123,
"generation_time_ms": 123,
"queue_time_ms": 123,
"mean_itl_ms": 123,
"tokens_per_second": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}Create chat completion
Generate a chat completion response from a deployed model.
curl --request POST \
--url https://flow.seekr.com/v1/inference/chat/completions \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "meta-llama/Llama-3.1-8B-Instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is the capital of France?"
}
],
"max_completion_tokens": 128,
"temperature": 0.7,
"stream": false
}
'import requests
url = "https://flow.seekr.com/v1/inference/chat/completions"
payload = {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is the capital of France?"
}
],
"max_completion_tokens": 128,
"temperature": 0.7,
"stream": False
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'meta-llama/Llama-3.1-8B-Instruct',
messages: [
{role: 'system', content: 'You are a helpful assistant.'},
{role: 'user', content: 'What is the capital of France?'}
],
max_completion_tokens: 128,
temperature: 0.7,
stream: false
})
};
fetch('https://flow.seekr.com/v1/inference/chat/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://flow.seekr.com/v1/inference/chat/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([
'model' => 'meta-llama/Llama-3.1-8B-Instruct',
'messages' => [
[
'role' => 'system',
'content' => 'You are a helpful assistant.'
],
[
'role' => 'user',
'content' => 'What is the capital of France?'
]
],
'max_completion_tokens' => 128,
'temperature' => 0.7,
'stream' => false
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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://flow.seekr.com/v1/inference/chat/completions"
payload := strings.NewReader("{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
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://flow.seekr.com/v1/inference/chat/completions")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://flow.seekr.com/v1/inference/chat/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is the capital of France?\"\n }\n ],\n \"max_completion_tokens\": 128,\n \"temperature\": 0.7,\n \"stream\": false\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "<string>",
"content": "<string>",
"refusal": "<string>",
"function_call": {
"name": "<string>",
"arguments": "<string>"
},
"tool_calls": [
{
"id": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
},
"type": "function"
}
],
"reasoning": "<string>"
},
"logprobs": {
"content": [
{
"token": "<string>",
"logprob": -9999,
"bytes": [
123
],
"top_logprobs": [
{
"token": "<string>",
"logprob": -9999,
"bytes": [
123
]
}
]
}
]
},
"finish_reason": "stop",
"stop_reason": 123,
"token_ids": [
123
]
}
],
"usage": {
"prompt_tokens": 0,
"total_tokens": 0,
"completion_tokens": 0,
"prompt_tokens_details": {
"cached_tokens": 123,
"created_cache_tokens": 123,
"multimodal_tokens": {}
}
},
"object": "chat.completion",
"service_tier": "auto",
"system_fingerprint": "<string>",
"prompt_logprobs": [
{}
],
"prompt_token_ids": [
123
],
"prompt_text": "<string>",
"metrics": {
"time_to_first_token_ms": 123,
"generation_time_ms": 123,
"queue_time_ms": 123,
"mean_itl_ms": 123,
"tokens_per_second": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": 123,
"param": "<string>"
}
}Authorizations
Body
Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
none, minimal, low, medium, high, xhigh, max If this is set, the chat will be formatted so that the final message in the chat is open-ended, without any EOS tokens. The model will continue this message rather than starting a new one. This allows you to "prefill" part of the model's response for it. Cannot be used at the same time as add_generation_prompt.
A list of dicts representing documents that will be accessible to the model if it is performing RAG (retrieval-augmented generation). If the template does not support RAG, this argument will have no effect. Each document should contain "title" and "text" keys.
Show child attributes
Show child attributes
Response
Successful response.