Chat Completions API

Create Chat Completions

Endpoint to generate conversational responses based on user-provided input messages.

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

Example Request

curl https://api.relax.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $RELAX_API_KEY" \
  -d '{
    "model": "Llama-4-Maverick-17B-128E",
    "messages": [{"role": "user", "content": "What is the capital of the UK?"}],
    "temperature": 0.7
  }'

import openai

client = OpenAI(
  api_key = RELAX_API_KEY,
  base_url = 'https://api.relax.ai/v1/',
)

response = client.chat.completions.create(
    model = "DeepSeek-R1-0528",
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me about climate change."}
    ],
    temperature = 0.7,
    max_tokens = 100
)

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

import { OpenAI } from "openai";

const openai = new OpenAI({
  apiKey: RELAX_API_KEY,
  baseUrl: 'https://api.relax.ai/v1/'
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: "user", content: "What is the capital of the UK?" }],
    model: "Llama-4-Maverick-17B-128E",
    temperature: 0.7
  });

  console.log(completion.choices[0]);
}

main();

Response

Returns a Chat Completions object.

Chat Completions Response

{
 "id": "chatcmpl-1c05717f8d68454f9375d6706cc275e6",
 "object": "chat.completion",
 "created": 1744034860,
 "model": "Llama-4-Maverick-17B-128E",
 "choices": [
  {
   "index": 0,
   "message": {
    "role": "assistant",
    "content": "The capital of the United Kingdom is London."
   },
   "finish_reason": "stop",
   "content_filter_results": {
    "hate": {
     "filtered": false
    },
    "self_harm": {
     "filtered": false
    },
    "sexual": {
     "filtered": false
    },
    "violence": {
     "filtered": false
    },
    "jailbreak": {
     "filtered": false,
     "detected": false
    },
    "profanity": {
     "filtered": false,
     "detected": false
    }
   }
  }
 ],
 "usage": {
  "prompt_tokens": 76,
  "completion_tokens": 10,
  "total_tokens": 86,
  "prompt_tokens_details": null,
  "completion_tokens_details": null
 },
 "system_fingerprint": ""
}

Request Body

The following parameters can be included in the request body:

Chat Completions Request Body

model

Type: string
Required: Yes
Description: The model name to use for generating the completion.

messages

Type: array
Required: Yes
Description: A list of message objects representing the conversation history.

temperature

Type: float
Required: No
Description: Controls randomness. Lower values make output more focused and deterministic.

top_p

Type: float
Required: No
Description: An alternative to temperature that controls diversity via nucleus sampling.

max_tokens

Type: integer
Required: No
Description: The maximum number of tokens to generate for the completion.

stop

Type: string
Required: No
Description: A sequence where the API will stop generating further tokens.

presence_penalty

Type: float
Required: No
Description: Penalizes new tokens based on whether they appear in the text so far.

frequency_penalty

Type: float
Required: No
Description: Penalizes new tokens based on their cumulative frequency in the generated text.

logprobs

Type: boolean
Required: No
Description: If set to true, returns the log probabilities of each token in the output.

user

Type: string
Required: No
Description: An optional identifier representing the end-user making the request.

Streaming

The relaxAI API supports response streaming, enabling clients to receive partial results for specific requests in real-time.

Streaming is available for the relaxAI Chat Completions endpoint. This section will cover streaming functions in Chat Completions, with examples on how to use.

python
node.js

import openai

client = OpenAI(
  api_key = RELAX_API_KEY,
  base_url = 'https://api.relax.ai/v1/',
)

stream = client.chat.completions.create(
  model="Llama-4-Maverick-17B-128E",
  messages=[
    {"role": "user", "content": "What is the capital of the UK?"}
  ],
  stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

import { OpenAI } from "openai";

const openai = new OpenAI({
  apiKey: RELAX_API_KEY,
  baseUrl: 'https://api.relax.ai/v1/'
});

async function main() {
    const stream = await openai.chat.completions.create({
        model: "Llama-4-Maverick-17B-128E",
        messages: [{ role: "user", content: "What is the capital of the UK?" }],
        store: true,
        stream: true,
    });
    for await (const chunk of stream) {
        process.stdout.write(chunk.choices[0]?.delta?.content || "");
    }
}

main();

Tool Calling

relaxAI supports tool calling to enable seamless integration of custom tools into your AI workflows, allowing you to define and pass bespoke functionality to the Chat Completions endpoint. This feature allows developers to extend the capabilities of our AI models with tools tailored to their specific use cases, enhancing the overall flexibility and effectiveness of their applications.

To use custom tools, you will need to define a list of functions the model may generate JSON inputs for. Currently a maximum of 128 functions may be defined.

python
node.js

import openai

client = OpenAI(
  api_key = RELAX_API_KEY,
  base_url = 'https://api.relax.ai/v1/',
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]
messages = [{"role": "user", "content": "What's the weather like in London today?"}]
completion = client.chat.completions.create(
  model="DeepSeek-R1-0528",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

import OpenAI from "openai";

const openai = new OpenAI({
apiKey: RELAX_API_KEY,
baseUrl: "https://api.relax.ai/v1/"
});

async function main() {
const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}];
const tools = [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
];

const response = await openai.chat.completions.create({
model: "DeepSeek-R1-0528",
messages: messages,
tools: tools,
tool_choice: "auto",
});

console.log(response);
}

main();