Create chat completion
curl --request POST \
--url https://gateway.errorbar.ai/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "Qwen/Qwen3-32B",
"messages": [
{
"content": "<unknown>"
}
],
"stream": false,
"stream_options": {},
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"stop": "<unknown>",
"seed": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"repetition_penalty": 123,
"logit_bias": {},
"logprobs": true,
"top_logprobs": 123,
"response_format": {},
"tools": [
{}
],
"tool_choice": "<unknown>",
"parallel_tool_calls": true,
"reasoning_effort": "<string>",
"user": "<string>",
"fallbacks": [
"<string>"
]
}
'import requests
url = "https://gateway.errorbar.ai/chat/completions"
payload = {
"model": "Qwen/Qwen3-32B",
"messages": [{ "content": "<unknown>" }],
"stream": False,
"stream_options": {},
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"stop": "<unknown>",
"seed": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"repetition_penalty": 123,
"logit_bias": {},
"logprobs": True,
"top_logprobs": 123,
"response_format": {},
"tools": [{}],
"tool_choice": "<unknown>",
"parallel_tool_calls": True,
"reasoning_effort": "<string>",
"user": "<string>",
"fallbacks": ["<string>"]
}
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({
model: 'Qwen/Qwen3-32B',
messages: [{content: '<unknown>'}],
stream: false,
stream_options: {},
temperature: 123,
top_p: 123,
top_k: 123,
n: 123,
max_tokens: 123,
max_completion_tokens: 123,
stop: '<unknown>',
seed: 123,
frequency_penalty: 123,
presence_penalty: 123,
repetition_penalty: 123,
logit_bias: {},
logprobs: true,
top_logprobs: 123,
response_format: {},
tools: [{}],
tool_choice: '<unknown>',
parallel_tool_calls: true,
reasoning_effort: '<string>',
user: '<string>',
fallbacks: ['<string>']
})
};
fetch('https://gateway.errorbar.ai/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://gateway.errorbar.ai/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' => 'Qwen/Qwen3-32B',
'messages' => [
[
'content' => '<unknown>'
]
],
'stream' => false,
'stream_options' => [
],
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'n' => 123,
'max_tokens' => 123,
'max_completion_tokens' => 123,
'stop' => '<unknown>',
'seed' => 123,
'frequency_penalty' => 123,
'presence_penalty' => 123,
'repetition_penalty' => 123,
'logit_bias' => [
],
'logprobs' => true,
'top_logprobs' => 123,
'response_format' => [
],
'tools' => [
[
]
],
'tool_choice' => '<unknown>',
'parallel_tool_calls' => true,
'reasoning_effort' => '<string>',
'user' => '<string>',
'fallbacks' => [
'<string>'
]
]),
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://gateway.errorbar.ai/chat/completions"
payload := strings.NewReader("{\n \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\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://gateway.errorbar.ai/chat/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.errorbar.ai/chat/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 \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\n}"
response = http.request(request)
puts response.read_body{
"id": "chatcmpl-...",
"object": "chat.completion",
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "assistant",
"content": "<string>",
"tool_calls": [
{}
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance. Please top up your wallet.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "The model 'x' does not exist or is not available.",
"type": "invalid_request_error",
"code": "model_not_found"
}
}Inference API
Create chat completion
Generate a model response for a conversation. OpenAI-compatible; supports streaming, tool calls, and structured output. Supports gateway fallback models (fallbacks) and, when the workspace has response caching enabled, serves identical repeat requests from cache at a discount (see the X-Errorbar-Cache response header).
POST
/
chat
/
completions
Create chat completion
curl --request POST \
--url https://gateway.errorbar.ai/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "Qwen/Qwen3-32B",
"messages": [
{
"content": "<unknown>"
}
],
"stream": false,
"stream_options": {},
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"stop": "<unknown>",
"seed": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"repetition_penalty": 123,
"logit_bias": {},
"logprobs": true,
"top_logprobs": 123,
"response_format": {},
"tools": [
{}
],
"tool_choice": "<unknown>",
"parallel_tool_calls": true,
"reasoning_effort": "<string>",
"user": "<string>",
"fallbacks": [
"<string>"
]
}
'import requests
url = "https://gateway.errorbar.ai/chat/completions"
payload = {
"model": "Qwen/Qwen3-32B",
"messages": [{ "content": "<unknown>" }],
"stream": False,
"stream_options": {},
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"stop": "<unknown>",
"seed": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"repetition_penalty": 123,
"logit_bias": {},
"logprobs": True,
"top_logprobs": 123,
"response_format": {},
"tools": [{}],
"tool_choice": "<unknown>",
"parallel_tool_calls": True,
"reasoning_effort": "<string>",
"user": "<string>",
"fallbacks": ["<string>"]
}
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({
model: 'Qwen/Qwen3-32B',
messages: [{content: '<unknown>'}],
stream: false,
stream_options: {},
temperature: 123,
top_p: 123,
top_k: 123,
n: 123,
max_tokens: 123,
max_completion_tokens: 123,
stop: '<unknown>',
seed: 123,
frequency_penalty: 123,
presence_penalty: 123,
repetition_penalty: 123,
logit_bias: {},
logprobs: true,
top_logprobs: 123,
response_format: {},
tools: [{}],
tool_choice: '<unknown>',
parallel_tool_calls: true,
reasoning_effort: '<string>',
user: '<string>',
fallbacks: ['<string>']
})
};
fetch('https://gateway.errorbar.ai/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://gateway.errorbar.ai/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' => 'Qwen/Qwen3-32B',
'messages' => [
[
'content' => '<unknown>'
]
],
'stream' => false,
'stream_options' => [
],
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'n' => 123,
'max_tokens' => 123,
'max_completion_tokens' => 123,
'stop' => '<unknown>',
'seed' => 123,
'frequency_penalty' => 123,
'presence_penalty' => 123,
'repetition_penalty' => 123,
'logit_bias' => [
],
'logprobs' => true,
'top_logprobs' => 123,
'response_format' => [
],
'tools' => [
[
]
],
'tool_choice' => '<unknown>',
'parallel_tool_calls' => true,
'reasoning_effort' => '<string>',
'user' => '<string>',
'fallbacks' => [
'<string>'
]
]),
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://gateway.errorbar.ai/chat/completions"
payload := strings.NewReader("{\n \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\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://gateway.errorbar.ai/chat/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.errorbar.ai/chat/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 \"model\": \"Qwen/Qwen3-32B\",\n \"messages\": [\n {\n \"content\": \"<unknown>\"\n }\n ],\n \"stream\": false,\n \"stream_options\": {},\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"stop\": \"<unknown>\",\n \"seed\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"repetition_penalty\": 123,\n \"logit_bias\": {},\n \"logprobs\": true,\n \"top_logprobs\": 123,\n \"response_format\": {},\n \"tools\": [\n {}\n ],\n \"tool_choice\": \"<unknown>\",\n \"parallel_tool_calls\": true,\n \"reasoning_effort\": \"<string>\",\n \"user\": \"<string>\",\n \"fallbacks\": [\n \"<string>\"\n ]\n}"
response = http.request(request)
puts response.read_body{
"id": "chatcmpl-...",
"object": "chat.completion",
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "assistant",
"content": "<string>",
"tool_calls": [
{}
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance. Please top up your wallet.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "The model 'x' does not exist or is not available.",
"type": "invalid_request_error",
"code": "model_not_found"
}
}Authorizations
Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer .
Headers
Per-request cache control (only meaningful when the workspace has response caching enabled — it can reduce caching, never enable it). no-cache: skip the cache and force a fresh model run, refreshing the stored copy. no-store: fresh run AND keep this response out of cache storage entirely. Either way the response carries X-Errorbar-Cache: bypass.
Available options:
no-cache, no-store Body
application/json
The model id, e.g. Qwen/Qwen3-32B. A dedicated endpoint is addressed as dedicated/.
Example:
"Qwen/Qwen3-32B"
The conversation so far.
Show child attributes
Show child attributes
Stream the response as server-sent events.
Streaming options. Usage reporting is included automatically.
Sampling temperature (0–2).
Nucleus sampling probability mass.
Top-k sampling.
Number of completions to generate.
Maximum output tokens. Bounded by the model's context window.
Alias for max_tokens.
Up to a few stop sequences (string or array of strings).
For more reproducible sampling.
Penalize repeated tokens by frequency.
Penalize tokens that have appeared.
Penalize repetition.
Bias specific tokens.
Return log probabilities.
How many top log probabilities to return per token.
{ "type": "json_object" } or { "type": "json_schema", ... } for structured output.
Function definitions the model may call.
auto, required, none, or a specific function.
Allow the model to call multiple tools in parallel.
Reasoning effort for reasoning-capable models.
A stable identifier for the end user.
Up to 2 backup model ids tried in order when the primary fails with a transient error (429/timeout/5xx). Billing uses the model that actually served; the X-Errorbar-Fallback-From response header names the model it fell back from. Gateway feature — never forwarded to the model.
Maximum array length:
2