Chat Completions

curl --request POST \
  --url https://api.redpill.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "temperature": 123,
  "max_tokens": 123,
  "max_completion_tokens": 123,
  "stream": true,
  "top_p": 123,
  "n": 123,
  "presence_penalty": 123,
  "frequency_penalty": 123,
  "provider": {}
}
'

import requests

url = "https://api.redpill.ai/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "temperature": 123,
    "max_tokens": 123,
    "max_completion_tokens": 123,
    "stream": True,
    "top_p": 123,
    "n": 123,
    "presence_penalty": 123,
    "frequency_penalty": 123,
    "provider": {}
}
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: '<string>',
    messages: [{}],
    temperature: 123,
    max_tokens: 123,
    max_completion_tokens: 123,
    stream: true,
    top_p: 123,
    n: 123,
    presence_penalty: 123,
    frequency_penalty: 123,
    provider: {}
  })
};

fetch('https://api.redpill.ai/v1/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://api.redpill.ai/v1/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'temperature' => 123,
    'max_tokens' => 123,
    'max_completion_tokens' => 123,
    'stream' => true,
    'top_p' => 123,
    'n' => 123,
    'presence_penalty' => 123,
    'frequency_penalty' => 123,
    'provider' => [
        
    ]
  ]),
  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.redpill.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\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.redpill.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.redpill.ai/v1/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\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\n}"

response = http.request(request)
puts response.read_body

POST

chat

completions

Chat Completions

curl --request POST \
  --url https://api.redpill.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "temperature": 123,
  "max_tokens": 123,
  "max_completion_tokens": 123,
  "stream": true,
  "top_p": 123,
  "n": 123,
  "presence_penalty": 123,
  "frequency_penalty": 123,
  "provider": {}
}
'

import requests

url = "https://api.redpill.ai/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "temperature": 123,
    "max_tokens": 123,
    "max_completion_tokens": 123,
    "stream": True,
    "top_p": 123,
    "n": 123,
    "presence_penalty": 123,
    "frequency_penalty": 123,
    "provider": {}
}
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: '<string>',
    messages: [{}],
    temperature: 123,
    max_tokens: 123,
    max_completion_tokens: 123,
    stream: true,
    top_p: 123,
    n: 123,
    presence_penalty: 123,
    frequency_penalty: 123,
    provider: {}
  })
};

fetch('https://api.redpill.ai/v1/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://api.redpill.ai/v1/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'temperature' => 123,
    'max_tokens' => 123,
    'max_completion_tokens' => 123,
    'stream' => true,
    'top_p' => 123,
    'n' => 123,
    'presence_penalty' => 123,
    'frequency_penalty' => 123,
    'provider' => [
        
    ]
  ]),
  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.redpill.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\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.redpill.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.redpill.ai/v1/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\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"max_completion_tokens\": 123,\n  \"stream\": true,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"presence_penalty\": 123,\n  \"frequency_penalty\": 123,\n  \"provider\": {}\n}"

response = http.request(request)
puts response.read_body

Create Chat Completion

Creates a model response for the given chat conversation. Requests are served through the attested TEE gateway, which does not retain request bodies. A confidential response additionally runs on a verified upstream enclave, confirmed per response from the receipt’s upstream.verified event. The response includes an x-receipt-id header for verification.

POST https://api.redpill.ai/v1/chat/completions

Try it now! Click the “Try it” button above to test the API in the playground. You’ll need:

Your API key (add it when prompted)
Fill in messages like: [{"role":"user","content":"Hello"}]

Request Body

string

default:"z-ai/glm-5.1"

required

Model ID to use for completionExamples: z-ai/glm-5.1, z-ai/glm-5, qwen/qwen3.5-27b, openai/gpt-5, anthropic/claude-sonnet-4.5

array

required

Array of message objects. Each message needs role and content.Example:

[
  {"role": "user", "content": "What is confidential AI?"}
]

With system message:

[
  {"role": "system", "content": "You are a helpful assistant"},
  {"role": "user", "content": "Hello!"}
]

number

Sampling temperature (0-2), default 1

integer

Maximum tokens to generateNote: Newer models (GPT-5, O3, O4) use max_completion_tokens instead. See note below.

integer

Maximum completion tokens (for GPT-5, O3, O4 models)Use this parameter instead of max_tokens for newer OpenAI models:

openai/gpt-5, openai/gpt-5-mini, openai/gpt-5-nano
openai/o3, openai/o4-mini

boolean

Stream responses, default false

number

Nucleus sampling (0-1)

integer

Number of completions, default 1

number

Presence penalty (-2 to 2)

number

Frequency penalty (-2 to 2)

object

Routing constraints for this request. Fields are applied together, and the request is served only by a provider that satisfies all of them.zdr (boolean): set true to route only to providers that operate under zero data retention, meaning they do not retain prompt or completion content after serving the request. false, or omitting the field, applies no retention constraint.

{"provider": {"zdr": true}}

If no provider for the model satisfies the constraint, the request returns 404 and no prompt is sent. The constraint is enforced for the whole request, including failover, so a retry cannot fall back to a provider that does not satisfy it.Find models that can satisfy zdr ahead of time with GET /v1/models?zdr=true. See Zero data retention.aci_verified (boolean): set true to route only to an upstream the gateway verified inside the TEE before sending the prompt. false, or omitting the field, applies no attestation constraint.

{"provider": {"aci_verified": true}}

If no upstream for the model is both classified as attested and currently verified, the request returns 503 and no prompt is sent. X-Upstream-Verification: none cannot relax this constraint.aci_session_ids (array of strings): restrict the request further to specific attested channels, identified by the session ids from GET /v1/aci/sessions. Any one of the listed ids may serve the request; if none matches a currently verified channel, the request returns 503.

{"provider": {"aci_verified": true, "aci_session_ids": ["as_2a44...6290"]}}

Session ids imply aci_verified. Passing them with "aci_verified": false returns 400, as does an empty array or a non-string entry. Both fields are read by the gateway and removed before the request reaches a provider. See Attested routing.

Message Object

{
  "role": "user" | "assistant" | "system",
  "content": "string" | array
}

Example Requests

curl https://api.redpill.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "z-ai/glm-5.1",
    "messages": [
      {"role": "user", "content": "What is confidential AI?"}
    ]
  }'

curl https://api.redpill.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [
      {"role": "user", "content": "What is confidential AI?"}
    ]
  }"

curl https://api.redpill.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4.5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain TEE"}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }"

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.redpill.ai/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[
        {"role": "system", "content": "You are helpful."},
        {"role": "user", "content": "Hello!"}
    ],
    temperature=0.7,
    max_tokens=100
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.redpill.ai/v1',
  apiKey: 'YOUR_API_KEY'
});

const response = await client.chat.completions.create({
  model: 'openai/gpt-5',
  messages: [
    { role: 'system', content: 'You are helpful.' },
    { role: 'user', content: 'Hello!' }
  ],
  temperature: 0.7,
  max_tokens: 100
});

console.log(response.choices[0].message.content);

Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "openai/gpt-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Confidential AI is a privacy-first approach to inference..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 25,
    "total_tokens": 38
  }
}

Important: Parameter Difference for Newer ModelsGPT-5, O3, and O4 models require max_completion_tokens instead of max_tokens:

# ❌ Doesn't work for GPT-5/O3/O4
client.chat.completions.create(
    model="openai/gpt-5",
    max_tokens=100  # Error: unsupported parameter
)

# ✅ Works for GPT-5/O3/O4
client.chat.completions.create(
    model="openai/gpt-5",
    max_completion_tokens=100  # Correct parameter
)

# ℹ️ Older models (GPT-4.1, Claude, etc.) still use max_tokens

Affected models:

openai/gpt-5, openai/gpt-5-mini, openai/gpt-5-nano
openai/o3, openai/o4-mini

Other models (use max_tokens):

All GPT-4.1 models, Claude models, Gemini, DeepSeek, and GPU TEE models

Streaming

Enable stream: true for real-time responses:

stream = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[{"role": "user", "content": "Write a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

const stream = await client.chat.completions.create({
  model: 'openai/gpt-5',
  messages: [{ role: 'user', content: 'Write a story' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Vision (Multimodal)

Use vision models with images:

response = client.chat.completions.create(
    model="qwen/qwen3-vl-30b-a3b-instruct",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {"type": "image_url", "image_url": {"url": "https://..."}}
        ]
    }]
)

Function Calling

Define tools/functions for the model to call:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
            },
            "required": ["location"]
        }
    }
}]

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[{"role": "user", "content": "What's the weather in SF?"}],
    tools=tools
)

Function Calling Guide

Learn more about function calling →

Error Handling

try:
    response = client.chat.completions.create(...)
except openai.AuthenticationError:
    print("Invalid API key")
except openai.RateLimitError:
    print("Rate limit exceeded")
except openai.BadRequestError as e:
    print(f"Bad request: {e}")

try {
  const response = await client.chat.completions.create(...);
} catch (error) {
  if (error.status === 401) {
    console.error('Invalid API key');
  } else if (error.status === 429) {
    console.error('Rate limit exceeded');
  }
}

Supported Models

GPU TEE: z-ai/glm-5.1, z-ai/glm-5, qwen/qwen3.5-27b
OpenAI: openai/gpt-5, openai/gpt-5-mini, openai/o4-mini
Anthropic: anthropic/claude-sonnet-4.5, anthropic/claude-opus-4.1
Google: google/gemini-2.5-pro
Meta: meta-llama/llama-3.3-70b-instruct
A broad range of models

All Models

View all supported models →

Endpoints

Verification

Legacy

Chat Completions

Create Chat Completion

Request Body

Message Object

Example Requests

Response

Streaming

Vision (Multimodal)

Function Calling

Function Calling Guide

Error Handling

Supported Models

All Models

​Create Chat Completion

​Request Body

​Message Object

​Example Requests

​Response

​Streaming

​Vision (Multimodal)

​Function Calling

Function Calling Guide

​Error Handling

​Supported Models

All Models

Create Chat Completion

Request Body

Message Object

Example Requests

Response

Streaming

Vision (Multimodal)

Function Calling

Error Handling

Supported Models