Introduction

Draftworks serves GPT-5.5 through an OpenAI-compatible API backed by Azure's inference fleet. You point your existing SDK at a different base URL and keep everything else — request shapes, response shapes, streaming, tool calls.

https://www.draftworks.dev/v1

Three things distinguish it from calling OpenAI directly:

1. Price. $4.00 per 1M input tokens and $24.00 per 1M output tokens — 20% under OpenAI list. Once your lifetime purchases reach $5,000, rates drop permanently to 25% under list. See pricing and credits.
2. Latency. Requests are served from Azure's inference fleet. Observed user-visible time-to-first-token is around 450 ms, and every response carries upstream latency telemetry in usage.latency_checkpoint — surfaced by Azure and passed through unmodified.
3. Verifiability. Every response is signed with Ed25519. The receipt commits to the model id, request and response hashes, and token counts — so you can prove, cryptographically, that you got what you paid for. See verification.

Billing is prepaid credits: 1 credit = $1 of inference at your tier's rates. Minimum purchase $5. No subscription, no seat fees.

Who this is for

• Teams already built on the OpenAI SDK who want the same model at a lower unit cost, with zero code changes beyond baseURL.
• Anyone who needs an auditable record of inference — the model actually used, the exact bytes in and out — for compliance, research, or dispute resolution.
• Workloads where prompt content must not be retained. Draftworks stores SHA-256 hashes and token counts only; see privacy.

Endpoints

All authenticated endpoints take Authorization: Bearer dw_live_.... See authentication.

The model

Embeddings, images, audio, batch, and fine-tuning are not offered. Requests to those endpoints return 404 today. See SDK compatibility.

Next steps

• Quickstart — first request in under five minutes
• Chat Completions reference
• Verification — how signed receipts work and how to check one