SDKs

Stockyard is OpenAI-compatible. Use any existing SDK.

The One-Line Change

Stockyard exposes the same /v1/chat/completions endpoint as OpenAI. To use it, point your existing SDK at your Stockyard instance and set your Stockyard API key. That's it.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://your-host/v1",
    api_key="sk-sy-YOUR_KEY",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello from Stockyard"}],
)
print(response.choices[0].message.content)

Works with streaming too:

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Count to 10"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

TypeScript / Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://your-host/v1",
  apiKey: "sk-sy-YOUR_KEY",
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello from Stockyard" }],
});
console.log(response.choices[0].message.content);

Go

package main

import (
    "context"
    "fmt"
    openai "github.com/sashabaranov/go-openai"
)

func main() {
    config := openai.DefaultConfig("sk-sy-YOUR_KEY")
    config.BaseURL = "https://your-host/v1"
    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "gpt-4o",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Hello from Stockyard"},
            },
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

curl

curl https://your-host/v1/chat/completions \
  -H "Authorization: Bearer sk-sy-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Routing Headers

Stockyard supports extra headers for routing and attribution that pass through any SDK:

# Python
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
    extra_headers={
        "X-Project": "my-app",
        "X-Provider": "anthropic",
        "X-Stockyard-Tags": "env=prod,team=backend",
    },
)

// TypeScript
const response = await client.chat.completions.create(
  {
    model: "gpt-4o",
    messages: [{ role: "user", content: "Hello" }],
  },
  {
    headers: {
      "X-Project": "my-app",
      "X-Provider": "anthropic",
      "X-Stockyard-Tags": "env=prod,team=backend",
    },
  }
);

Any OpenAI-Compatible SDK

Stockyard works with any library that targets the OpenAI API: LiteLLM, LangChain, Vercel AI SDK, Instructor, and more. Just change the base URL and API key.