SDK compatibility

Draftworks implements the OpenAI wire format. The rule of thumb: anything that lets you set an OpenAI-compatible base URL works. Set it to:

https://www.draftworks.dev/v1

Compatibility matrix

Chat Completions, the Responses API, streaming, tool calling, structured outputs, and vision inputs all pass through unchanged, so framework features built on those primitives (agents, output parsers, function-calling abstractions) work as they do against OpenAI.

Official OpenAI SDKs

from openai import OpenAI

client = OpenAI(
    base_url="https://www.draftworks.dev/v1",
    api_key="dw_live_...",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://www.draftworks.dev/v1",
  apiKey: process.env.DRAFTWORKS_API_KEY,
});

Both client.chat.completions and client.responses work, including .stream() helpers.

Vercel AI SDK

import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const draftworks = createOpenAI({
  baseURL: "https://www.draftworks.dev/v1",
  apiKey: process.env.DRAFTWORKS_API_KEY,
});

const { text } = await generateText({
  model: draftworks("gpt-5.5"),
  prompt: "Summarize RFC 9110 section 9 in five bullets.",
});

streamText and tool calling work as with any OpenAI provider instance.

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-5.5",
    base_url="https://www.draftworks.dev/v1",
    api_key="dw_live_...",
)

LlamaIndex

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="gpt-5.5",
    api_base="https://www.draftworks.dev/v1",
    api_key="dw_live_...",
    is_chat_model=True,
)

LiteLLM

Prefix the model with openai/ so LiteLLM routes it as an OpenAI-compatible provider:

from litellm import completion

response = completion(
    model="openai/gpt-5.5",
    api_base="https://www.draftworks.dev/v1",
    api_key="dw_live_...",
    messages=[{"role": "user", "content": "ping"}],
)

The same values work in LiteLLM Proxy config (model: openai/gpt-5.5, api_base, api_key).

Editor and agent tools

Continue, Cursor-style assistants, aider, and similar tools accept a custom OpenAI-compatible provider: set the base URL to https://www.draftworks.dev/v1, the API key to your dw_live_... key, and the model to gpt-5.5.

Not implemented

Draftworks serves GPT-5.5 inference only. The following OpenAI endpoints are not implemented. Any /v1/* path that Draftworks does not serve returns 404 with type: "invalid_request_error" and code: "unknown_endpoint", and a message naming the implemented endpoints (/v1/chat/completions, /v1/responses, /v1/models, /v1/receipts/{id}):

• Embeddings (/v1/embeddings)
• Images (/v1/images/*)
• Audio — speech, transcription, translation (/v1/audio/*)
• Batch (/v1/batches)
• Fine-tuning (/v1/fine_tuning/*)

If a framework feature depends on one of these (e.g. a vector-store integration calling embeddings), point that feature at a different provider and route only chat/responses traffic through Draftworks. Frameworks above all support per-capability provider configuration.

Anything else

If a tool speaks the OpenAI wire format but is not listed here, it almost certainly works. The two integration details worth knowing in advance: streamed responses end with an extra usage-bearing chunk (OpenAI-standard, see streaming), and error responses use the standard OpenAI envelope with one extra code, insufficient_credits (see errors).