Build AI Apps. Faster.

Access powerful AI models through a simple API with low-latency inference and smart model routing.

Get started freeView documentation

Trusted by

    • DOS.Me
    • MetaDOS
    • DOSafe
    • Heno
    • DOScan
    • OverMint
    • DOSwap

Why use DOS?

Build faster, scale easier, and focus on what matters - your product.

See a dated, reproducible benchmark snapshot with its exact workload and measured results.

Benchmark snapshotAugust 11, 2026
Time to First Token
1.069sec
Output throughput
1,855tok/s
Failed requests
0 / 600
Measured workload
dos-ai
1,024 input / 256 output tokens
concurrency 64
Snapshot, not a guarantee. Results vary by prompt, load, route, and model.

Run the best AI models with a single line of code

Access leading open-source and proprietary models for chat, images, code, and more - with smart routing built in.

Model Library

Access open-source and proprietary models for chat, images, video, code, embeddings, and audio.

Drop-in replacement for OpenAI - just change the base URL.

Start building now
CHATCODEVISION
D

DOS.AI Auto

Smart Router|128K ctx
Auto-priced
CHATCODE
D

DOS.AI

35B MoE (3B active)|128K ctx
$0.07 / 1M tokens
CHATCODE

DeepSeek V4 Flash

MoE (fast tier)|1M ctx
$0.15 / 1M tokens
CHATVISION

Gemini 3.1 Pro

Pro|1M ctx
$2.1 / 1M tokens
CHATCODEVISION

Claude Sonnet 5

Sonnet|1M ctx
$3.15 / 1M tokens
CHATCODEVISION
NEW

Claude Opus 5

Opus|1M ctx
$5.25 / 1M tokens
CHATCODEVISION

GPT-5.6 Sol

Frontier|1M ctx
$5.25 / 1M tokens

What can you build on DOS?

From chatbots to autonomous agents, DOS powers the next generation of AI applications.

Conversational AI

Build intelligent chatbots and virtual assistants.

Create AI-powered chat experiences with multi-turn conversations, context awareness, and natural language understanding.

AI

Support Agent

Online

AI

Hi! How can I help you today?

I need to reset my API key

AI

I've revoked your old key and generated a new one:

dos_sk_live_7f3a...x9k2

Copied to clipboard. The old key is now inactive.

Thanks! Can you also check my usage this month?

AI

Here's your usage summary:

API Calls12,847
Tokens2.4M
Cost$8.42
Type a message...

Code Assistant

Accelerate development with AI-powered coding.

Generate code, detect bugs, review pull requests, and create documentation automatically with state-of-the-art code models.

api-handler.ts
utils.py
123456789101112131415161718

import { streamText } from 'ai'

import { createDOS } from '@dos/sdk'

// AI-generated: streaming chat endpoint

 

const dos = createDOS()

 

export async function POST(req) {

const { messages } = await req.json()

 

const result = streamText({

model: dos('dos-ai'),

messages,

temperature: 0.7,

})

 

return result.toDataStreamResponse()

}

 

// Handle errors and rate limiting

AI: Add error handling with retry logic?Tab to accept

RAG & Search

Build powerful semantic search experiences.

Create knowledge bases with retrieval-augmented generation for accurate, contextual answers with citation support.

How do I configure rate limiting?
AI Answer3 sources

To configure rate limiting, add the rateLimit option to your API configuration:

const config = {
  rateLimit: {
    requests: 100,
    window: '1m'
  }
}

This limits each API key to 100 requests per minute. You can also set per-endpoint limits.

Sources

Rate Limiting Guide

docs/guides/rate-limiting.md

97%

API Configuration Reference

docs/api/config.md

89%

Security Best Practices

docs/guides/security.md

82%

AI Agents

Deploy autonomous AI agents on any channel.

Launch personal assistants, sales bots, and customer service agents on Telegram, WhatsApp, and more - with built-in memory, skills, and tool use.

C

Sales Assistant

Active on 3 channels

Running
Telegram
WhatsApp
Web Chat
Zalo

Conversations

1,247

+12%

Resolved

94.2%

+3%

Avg Response

1.2s

-0.3s

Recent Conversations

MT

Minh T.

2m ago

I want to order 50 units of SKU-4421

Active
SL

Sarah L.

5m ago

Do you ship internationally?

Resolved
NH

Nguyen H.

8m ago

Can I get a bulk discount?

Resolved
Skills:Product CatalogOrder TrackingDiscount RulesFAQ

Get started today

Start building with DOS in minutes. No credit card required. Get $5 in free credits to explore our API.

Start building for free

Frequently asked questions

Can’t find what you’re looking for? Reach out to our support team at support@dos.ai.

    • What models does DOS support?

      DOS provides access to leading open-source and proprietary models including Llama 4, DeepSeek, Qwen, Gemma, Mistral, and more. Use dos-auto to let our smart router pick the best model for each request automatically.

    • How does pricing work?

      We use pay-as-you-go pricing based on metered usage. There is no minimum commitment, and current rates are published by model.

    • Is there a free tier?

      Yes. New users get $5 in free credits to explore the API before adding funds.

    • How fast is the inference?

      Performance depends on the selected route, model, prompt, and load. Our public benchmark snapshot includes its workload and measured results.

    • Which AI models can I access?

      You get a wide range of models through one API - our own low-cost DOS.AI model plus frontier models from OpenAI, Anthropic, Google, DeepSeek, Qwen, and more. Use dos-auto to automatically route each request to the best model for the job.

    • Is my data secure?

      DOS uses TLS in transit, scoped API access, and managed secret references. Requests may be processed by the model provider selected for the route.

    • Do you offer enterprise plans?

      Contact our team to discuss dedicated resources, support, and deployment requirements.

    • What SDKs do you provide?

      Our REST API is compatible with OpenAI client libraries. The documentation includes a quickstart and API reference.

    • How do I get support?

      Use our documentation and community Discord, or contact support@dos.ai for account-specific help.