Examples

Working, copy-paste recipes for the ORVYX API. Every snippet runs against the same base URL and the same key, so you can move between them freely.

Before you start

You need an ORVYX API key (oryx_...). Create one in the dashboard under API Keys, then export it:

export ORVYX_API_KEY="oryx_..."

Pick a recipe

Chat CompletionSend a prompt and read the response in Python, Node.js, PHP, Rust, Go or Laravel.Start hereStreaming ResponsesConsume server-sent events token by token for real-time interfaces.SSETool CallingLet the model call your functions and feed the results back in a loop.Structured OutputGet strict JSON back from a model instead of prose.JSONEmbeddingsTurn text into vectors for search, clustering and retrieval.List ModelsDiscover every model available behind the single endpoint.

Frameworks covered

Every recipe ships with a Frameworks section, so you can copy the wiring for the stack you already run instead of translating from scratch.

Language	Frameworks
curl	no setup: curl and jq are enough
Python	FastAPI, Django, Flask
JavaScript / TypeScript	Express, Next.js, ws for WebSocket bridges
PHP	Laravel (controller, streamed response, queued job)
Rust	reqwest with tokio and futures
Go	standard library, Gin

Transports are covered too: every streaming recipe that needs one shows the SSE, WebSocket or polling shape, and says which trade-off you are accepting.

A minimal request

Every example below is a variation on this shape: point an OpenAI-compatible client at ORVYX, pick a model by id, send messages.

curl

curl https://api.orvyx-ai.com/v1/chat/completions \
  -H "Authorization: Bearer $ORVYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "orvyx/deepseek-v4-pro-0813",
    "messages": [{ "role": "user", "content": "Hello from ORVYX." }]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orvyx-ai.com/v1",
    api_key="oryx_...",
)

completion = client.chat.completions.create(
    model="orvyx/deepseek-v4-pro-0813",
    messages=[{"role": "user", "content": "Hello from ORVYX."}],
)

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

Node.js

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.orvyx-ai.com/v1",
  apiKey: process.env.ORVYX_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "orvyx/deepseek-v4-pro-0813",
  messages: [{ role: "user", content: "Hello from ORVYX." }],
})

console.log(completion.choices[0].message.content)

PHP

<?php

$ch = curl_init('https://api.orvyx-ai.com/v1/chat/completions');
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . getenv('ORVYX_API_KEY'),
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'model' => 'orvyx/deepseek-v4-pro-0813',
        'messages' => [['role' => 'user', 'content' => 'Hello from ORVYX.']],
    ]),
]);

$res = json_decode(curl_exec($ch), true);
curl_close($ch);

echo $res['choices'][0]['message']['content'];

Laravel

<?php

use Illuminate\Support\Facades\Http;

$res = Http::withToken(config('services.orvyx.key'))
    ->post('https://api.orvyx-ai.com/v1/chat/completions', [
        'model' => 'orvyx/deepseek-v4-pro-0813',
        'messages' => [['role' => 'user', 'content' => 'Hello from ORVYX.']],
    ])
    ->throw()
    ->json();

echo $res['choices'][0]['message']['content'];

Rust

use reqwest::Client;
use serde_json::json;

let client = Client::new();
let res = client
    .post("https://api.orvyx-ai.com/v1/chat/completions")
    .bearer_auth(std::env::var("ORVYX_API_KEY").unwrap())
    .json(&json!({
        "model": "orvyx/deepseek-v4-pro-0813",
        "messages": [{ "role": "user", "content": "Hello from ORVYX." }]
    }))
    .send()
    .await?
    .json::<serde_json::Value>()
    .await?;

println!("{}", res["choices"][0]["message"]["content"]);

Go

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

func main() {
	body, _ := json.Marshal(map[string]any{
		"model": "orvyx/deepseek-v4-pro-0813",
		"messages": []map[string]string{
			{"role": "user", "content": "Hello from ORVYX."},
		},
	})

	req, _ := http.NewRequest("POST", "https://api.orvyx-ai.com/v1/chat/completions", bytes.NewReader(body))
	req.Header.Set("Authorization", "Bearer "+os.Getenv("ORVYX_API_KEY"))
	req.Header.Set("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()

	var out struct {
		Choices []struct {
			Message struct {
				Content string `json:"content"`
			} `json:"message"`
		} `json:"choices"`
	}
	json.NewDecoder(res.Body).Decode(&out)

	fmt.Println(out.Choices[0].Message.Content)
}

Each snippet above has Copy, ChatGPT and Claude buttons in the top-right corner: copy it straight into your project, or open it in a chat to ask follow-up questions.

What every response shares

Field	Meaning
id	Unique request id, also returned as the x-request-id header
model	The catalogue id that actually served the request
usage	Token counts used for metering
choices	One entry per completion, with message and finish_reason

Next steps

• API Reference for every parameter and status code.
• Error Handling for the error envelope and retries.
• Rate Limits to pace your requests before throttling.