List available models
curl --request GET \
--url https://llm-gateway.assemblyai.com/v1/modelsimport requests
url = "https://llm-gateway.assemblyai.com/v1/models"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://llm-gateway.assemblyai.com/v1/models', 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://llm-gateway.assemblyai.com/v1/models",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://llm-gateway.assemblyai.com/v1/models"
req, _ := http.NewRequest("GET", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://llm-gateway.assemblyai.com/v1/models")
.asString();require 'uri'
require 'net/http'
url = URI("https://llm-gateway.assemblyai.com/v1/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_body{
"data": [
{
"id": "qwen3.5-4b-32k-fast",
"name": "Qwen3.5 4B Fast",
"description": "",
"creator": "Qwen",
"context_length": 32768,
"supported_parameters": [
"max_tokens",
"temperature",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 32768,
"max_completion_tokens": 8192
},
"pricing": {
"global": {
"prompt": 0.1,
"completions": 0.5
}
},
"retirement_date": 0,
"available_regions": [
"us",
"eu"
]
},
{
"id": "claude-sonnet-4-6",
"name": "Sonnet 4.6",
"description": "",
"creator": "Claude",
"context_length": 200000,
"supported_parameters": [
"max_tokens",
"temperature",
"tools",
"tool_choice",
"response_format",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 200000,
"max_completion_tokens": 128000
},
"pricing": {
"global": {
"prompt": 3,
"completions": 15,
"input_cache_read": 0.3,
"input_cache_write": 3.75,
"input_cache_write_1h": 6
},
"regional_increase_percent": 0.1
},
"retirement_date": 0,
"available_regions": [
"us",
"eu",
"global"
]
},
{
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"description": "",
"creator": "Google",
"context_length": 1048576,
"supported_parameters": [
"max_tokens",
"response_format",
"temperature",
"tools",
"tool_choice",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 1048576,
"max_completion_tokens": 65535
},
"pricing": {
"global": {
"prompt": 0.1,
"completions": 0.4,
"input_cache_read": 0.01
},
"regional_increase_percent": 0.1
},
"retirement_date": 0,
"available_regions": [
"us",
"eu",
"global"
]
}
]
}{
"code": 123,
"message": "<string>",
"request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"metadata": {
"errors": [
"<string>"
]
}
}API reference
List available models
To use our EU server for LLM Gateway, replace
llm-gateway.assemblyai.com with llm-gateway.eu.assemblyai.com.Returns the list of models available through LLM Gateway, including the supported parameters, context length, pricing, and regional availability of each model. This endpoint doesn’t require authentication.
GET
/
models
List available models
curl --request GET \
--url https://llm-gateway.assemblyai.com/v1/modelsimport requests
url = "https://llm-gateway.assemblyai.com/v1/models"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://llm-gateway.assemblyai.com/v1/models', 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://llm-gateway.assemblyai.com/v1/models",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://llm-gateway.assemblyai.com/v1/models"
req, _ := http.NewRequest("GET", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://llm-gateway.assemblyai.com/v1/models")
.asString();require 'uri'
require 'net/http'
url = URI("https://llm-gateway.assemblyai.com/v1/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_body{
"data": [
{
"id": "qwen3.5-4b-32k-fast",
"name": "Qwen3.5 4B Fast",
"description": "",
"creator": "Qwen",
"context_length": 32768,
"supported_parameters": [
"max_tokens",
"temperature",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 32768,
"max_completion_tokens": 8192
},
"pricing": {
"global": {
"prompt": 0.1,
"completions": 0.5
}
},
"retirement_date": 0,
"available_regions": [
"us",
"eu"
]
},
{
"id": "claude-sonnet-4-6",
"name": "Sonnet 4.6",
"description": "",
"creator": "Claude",
"context_length": 200000,
"supported_parameters": [
"max_tokens",
"temperature",
"tools",
"tool_choice",
"response_format",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 200000,
"max_completion_tokens": 128000
},
"pricing": {
"global": {
"prompt": 3,
"completions": 15,
"input_cache_read": 0.3,
"input_cache_write": 3.75,
"input_cache_write_1h": 6
},
"regional_increase_percent": 0.1
},
"retirement_date": 0,
"available_regions": [
"us",
"eu",
"global"
]
},
{
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"description": "",
"creator": "Google",
"context_length": 1048576,
"supported_parameters": [
"max_tokens",
"response_format",
"temperature",
"tools",
"tool_choice",
"stream"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"top_provider": {
"is_moderated": false,
"context_length": 1048576,
"max_completion_tokens": 65535
},
"pricing": {
"global": {
"prompt": 0.1,
"completions": 0.4,
"input_cache_read": 0.01
},
"regional_increase_percent": 0.1
},
"retirement_date": 0,
"available_regions": [
"us",
"eu",
"global"
]
}
]
}{
"code": 123,
"message": "<string>",
"request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"metadata": {
"errors": [
"<string>"
]
}
}Response
Successful response containing the list of available models.
The response returned by the models endpoint.
The list of models available through LLM Gateway.
Show child attributes
Show child attributes
Was this page helpful?
⌘I