Receive
Accept one OpenAI-compatible request.
POST /v1/chat/completionsOne OpenAI-compatible endpoint routes every request across Lite, Pro, or Max — from real-time speed to million-token reasoning.
The application sends one familiar request. DMS reads what the work demands before a model ever answers.
Lite for latency. Pro for precision. Max for context. One response contract comes back to your product.
dms-auto-routerThe endpoint profiles every request by latency, precision, and context before it selects a tier. Your client keeps one response contract from first token to final output.
Accept one OpenAI-compatible request.
POST /v1/chat/completionsRead the latency, precision, and context signals.
workload.profileSelect the strongest available tier for the work.
dms-auto-routerReturn one consistent response shape.
200 OK · SSELite, Pro, and Max are operating profiles—not a list of model names. Each one is tuned around the constraint that matters most to the work.
lite-64kSpeed & volume
pro-256kMost popularCode & precision
max-1mFlagshipReasoning & context
One OpenAI-compatible endpoint routes each workload to the model tier built for it.
Model selection and streamingYour knowledge layer grounds the request without turning private data into training material.
Retrieval and context assemblyTool-aware models choose the next operation, return structured output, and continue the workflow.
Tool use and orchestrationPolicies, deployment boundaries, and audit signals keep production workloads observable.
Policy and audit controlsThe application keeps a familiar interface while routing, context, tools, and deployment controls stay visible underneath.
Keep the SDK your team already knows. Change the base URL and model ID.
Move from fast conversations to coding and long-context reasoning without rebuilding the integration.
Start on shared infrastructure, then scope dedicated or private deployment with the DMS team.
The integration stays familiar while your team gains access to DMS model tiers and production deployment options.
import OpenAI from "openai";
const dms = new OpenAI({
apiKey: process.env.DMSLAB_API_KEY,
baseURL: "https://api.dmslab.ai/v1",
});
const response = await dms.chat.completions.create({
model: "dms-auto-router",
messages: [
{ role: "user", content: "Review this production change." }
],
stream: true,
});route = "lite-64k" · stream = trueLatency-prioritized routing for chat, classification, and interactive agents.
Start with the managed API. Move toward reserved or private infrastructure when your workload and controls demand it.
Choose the workload profile that fits today. Prices stay synced with the existing DMS API; dedicated and private infrastructure remain a separate enterprise path.
Low-latency inference for customer-facing chat and real-time agents.
$2.50/wk64KStructured generation accuracy and multi-file coherence for precision-sensitive work.
$6/wk256KLong-context reasoning and multi-step agent orchestration at scale.
$25/wk1MUse the shared API today, or work with DMS Lab on capacity, network boundaries, and deployment architecture.