cURL
curl --request GET \
--url https://models.relace.ai/v1/models \
--header 'Authorization: Bearer <token>'import requests
url = "https://models.relace.ai/v1/models"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://models.relace.ai/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://models.relace.ai/v1/models",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($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://models.relace.ai/v1/models"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://models.relace.ai/v1/models")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://models.relace.ai/v1/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"object": "list",
"data": [
{
"id": "deepseek-ai/DeepSeek-V4.1-Flash",
"object": "model",
"owned_by": "relace",
"name": "DeepSeek: DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek with 552B total parameters (8B active per input token), Engram conditional memory, and a 1M-token context window.",
"created": 1789006620,
"quantization": "fp4",
"input_modalities": [
{
"type": "text",
"supported_inputs": {
"max_context_length": {
"value": 1048576,
"unit": "token"
}
},
"pricing": [
{
"type": "prompt",
"unit": "token",
"cost_usd": "0.00000013"
},
{
"type": "cached_prompt",
"unit": "token",
"cost_usd": "0.00000001"
}
]
}
],
"output_modalities": [
{
"type": "text",
"max_length": {
"value": 1048576,
"unit": "token"
},
"streaming": true,
"supported_parameters": {
"temperature": {
"type": "unknown"
},
"max_tokens": {
"type": "integer",
"min": 1,
"max": 1048576,
"unit": "token"
},
"reasoning": {
"type": "boolean"
},
"tools": {
"type": "boolean"
}
},
"pricing": [
{
"type": "completion",
"unit": "token",
"cost_usd": "0.00000052"
}
]
}
]
}
]
}{
"error": "Invalid API key. Check the key, or create one at https://app.relace.ai."
}Open Models
List Models
The catalog of models your account can call, with each model’s current per-token prices, context limit and supported parameters. Prices change over time; poll this endpoint to track them. Entries are OpenAI model objects (object: "model", owned_by: "relace"), so client.models.list() in any OpenAI SDK pointed at https://models.relace.ai/v1 works.
GET
/
v1
/
models
cURL
curl --request GET \
--url https://models.relace.ai/v1/models \
--header 'Authorization: Bearer <token>'import requests
url = "https://models.relace.ai/v1/models"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://models.relace.ai/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://models.relace.ai/v1/models",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($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://models.relace.ai/v1/models"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://models.relace.ai/v1/models")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://models.relace.ai/v1/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"object": "list",
"data": [
{
"id": "deepseek-ai/DeepSeek-V4.1-Flash",
"object": "model",
"owned_by": "relace",
"name": "DeepSeek: DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek with 552B total parameters (8B active per input token), Engram conditional memory, and a 1M-token context window.",
"created": 1789006620,
"quantization": "fp4",
"input_modalities": [
{
"type": "text",
"supported_inputs": {
"max_context_length": {
"value": 1048576,
"unit": "token"
}
},
"pricing": [
{
"type": "prompt",
"unit": "token",
"cost_usd": "0.00000013"
},
{
"type": "cached_prompt",
"unit": "token",
"cost_usd": "0.00000001"
}
]
}
],
"output_modalities": [
{
"type": "text",
"max_length": {
"value": 1048576,
"unit": "token"
},
"streaming": true,
"supported_parameters": {
"temperature": {
"type": "unknown"
},
"max_tokens": {
"type": "integer",
"min": 1,
"max": 1048576,
"unit": "token"
},
"reasoning": {
"type": "boolean"
},
"tools": {
"type": "boolean"
}
},
"pricing": [
{
"type": "completion",
"unit": "token",
"cost_usd": "0.00000052"
}
]
}
]
}
]
}{
"error": "Invalid API key. Check the key, or create one at https://app.relace.ai."
}The catalog of every model your account can call — the open-weight models and the Relace models alike — with the current price of each. Use the
id field as the model parameter in Chat Completions and Messages requests.
Entries are OpenAI model objects (object: "model", owned_by: "relace") with the model’s context limit, modalities, prices and supported parameters added, so client.models.list() in any OpenAI SDK pointed at https://models.relace.ai/v1 works unchanged.
Tracking prices
Prices are subject to change, and this endpoint is the source of truth: the tables in these docs are updated by hand and can lag. Each entry carries its per-token prices as decimal dollar strings:input_modalities[].pricing(on thetextentry):promptfor input tokens and, where the model has a prefix cache,cached_promptfor input tokens served from it.output_modalities[].pricing:completionfor output tokens.