Skip to content
One SDK for your entire backend

One key. One wallet. One bill.

Don't stitch together 30 SDKs, juggle 30 keys, or reconcile 30 invoices at month-end. infrai puts 14 production modules and the vendors behind them under one contract, with transparent pricing and per-call metadata — swap a vendor without touching your code.

14
GA modules
93
API routes
0%
China-AI markup
1
Bill
python
from infrai import infra
infra.activate()

Two lines to activate. Ship the rest today.

Routes across the vendors you already trust

OpenAIAnthropicGoogleDeepSeekQwenStripeTwilioResendCloudflare R2PusherMixpanelSora

14 modules, one import

Every module is a thin, clean contract over best-in-class vendors. Pick a capability; infrai picks the route.

AI Runtime

/v1/ai

Chat, embeddings, vision, image, speech-to-text and text-to-speech across every major model.

ai.chatai.embedai.imageai.vision
7 routesAPI reference

AI Video

/v1/video

Text-to-video generation and job tracking across the leading video models.

video.generatevideo.statusvideo.cancel
3 routesAPI reference

Email

/v1/email

Transactional email with domain verification, suppression, and delivery tracking.

email.sendemail.getemail.listemail.suppress
7 routesAPI reference

SMS & OTP

/v1/sms

Programmable SMS, one-time-passcode send and verify, with delivery status.

sms.sendsms.otpsms.verifysms.status
9 routesAPI reference

Scheduling

/v1/scheduling

Cron jobs, queues, and webhooks — durable background work without a worker fleet.

scheduling.cron.createscheduling.cron.listscheduling.queue.publishscheduling.queue.consume
10 routesAPI reference

Observability

/v1/observability

Error capture, events, spans, metrics, and feature flags in one pipe.

observability.error.captureobservability.event.trackobservability.span.reportobservability.metric.report
7 routesAPI reference

Public URL

/v1/public-url

Instant shareable URLs and custom domains for whatever you ship.

public_url.createpublic_url.claimpublic_url.domain.createpublic_url.get
6 routesAPI reference

Captcha

/v1/captcha

Human-verification widgets and server-side verification across providers.

captcha.verifycaptcha.widget.create
2 routesAPI reference

PDF

/v1/pdf

Generate, merge, split, OCR, and watermark documents on demand.

pdf.generatepdf.mergepdf.splitpdf.ocr
5 routesAPI reference

Image Processing

/v1/image

Resize, compress, convert, and read metadata through one endpoint.

image.processimage.metadata
2 routesAPI reference

Realtime

/v1/realtime

Channels, presence, and publish, with auth tokens issued for you.

realtime.token.issuerealtime.channel.createrealtime.publishrealtime.presence.get
5 routesAPI reference

Storage

/v1/storage

Buckets and presigned object access across S3-compatible providers.

storage.bucket.createstorage.bucket.liststorage.object.presignstorage.object.delete
4 routesAPI reference

Analytics

/v1/analytics

Track, identify, funnels, and cohorts — product analytics without the wiring.

analytics.trackanalytics.identifyanalytics.funnelanalytics.cohort
4 routesAPI reference

Billing

/v1/billing

Charges and refunds behind a single, idempotent contract.

billing.charge.createbilling.charge.getbilling.refund.create
4 routesAPI reference

Account & control plane

Activation, wallet, keys, tier, and BYOK — the 18 control-plane routes you never have to wire up yourself.

account.activateaccount.balanceaccount.topupaccount.keys.create

One contract, every vendor underneath

infrai normalizes the providers below behind stable capability ids — swap vendors without touching your code.

AI models

OpenAIAnthropicGoogleDeepSeek0% markupQwen0% markupHunyuan0% markupDoubao0% markupMiniMax0% markupMistralAzureBedrockReplicateElevenLabs

Video models

SoraVeoKlingRunwayLumaPikaViduWanxiangHailuoDoubao Video

Email

ResendSendGridPostmarkMailgunMailjetSESAliyun DMTencent SES

SMS

TwilioPlivoAliyun SMSTencent SMS

Storage

S3R2GCSAliyun OSS

Realtime

PusherAblyLiveblocks

Captcha

TurnstilehCaptchareCAPTCHA v3

Image

CloudinaryImageKitTinyPNG

PDF

DocRaptorPDFShift

Analytics

MixpanelAmplitudePostHogInfrai Native

Payments

StripeAlipayWeChat PayAdyenStripe Connect

Built to stay up — and stay safe

One endpoint in front of every vendor, with failover, idempotency and encrypted keys on by default.

Automatic multi-vendor failover

When a vendor degrades or rate-limits, traffic fails over to a healthy one automatically — cost-capped at 1.5× (up to 3× on Enterprise). Your app keeps calling one stable endpoint.

Idempotent by default

Every write takes an idempotency key, so retries are safe and effects apply exactly once — no double charges, no duplicate sends.

Your keys, encrypted and scoped

BYOK and platform credentials are stored in KMS and shown only once. Scope each key to specific capabilities and lock it to an IP allowlist.

Enterprise-grade compliance

SOC 2 and HIPAA, SSO via SAML/OIDC, full audit logs, and a 99.99% uptime SLA on Enterprise.

Pricing you can actually predict

No minimum markup, no small-request fee. Pick a plan; usage is billed transparently on top.

Standard

$0/ month
Wallet cap$500
Failover up to 1.5× cost
1 GB bandwidth free
  • $2 trial credit included
  • Wallet up to $500
  • BYOK: 8 modules, 30-day trial
  • Failover up to 1.5× cost
  • Unused credit forfeits after 12 months
Start free
Most popular

Pro

$20/ month

or $200/year — save 17%

Wallet cap$5,000
Failover up to 1.5× cost
100 GB bandwidth free
  • Wallet up to $5,000
  • 5× rate limits
  • BYOK: 8 modules, permanent
  • Auto-recharge
  • Failover chain
Upgrade to Pro

Enterprise

$1,500+
Wallet capNo wallet — invoice
Failover up to 3× cost
1 TB+ bandwidth free
  • Invoice post-pay (NET 30/60/90)
  • SOC 2 / HIPAA
  • SSO / SCIM / audit log
  • BYOC / dedicated tenant
  • 99.99% SLA · failover up to 3.0× cost
Contact sales

Transparent, usage-based pricing

What you see is what you pay. No minimum markup, no per-request fee — here's exactly how usage is priced.

Chinese AI vendors

0% markup

DeepSeek, Qwen, Hunyuan, Doubao, MiniMax billed at vendor list price — not a cent more.

Western AI vendors

5% markup

OpenAI, Anthropic, Google, Mistral and others — billed at vendor cost plus a flat 5%.

Batch API

100% passthrough

Opt into a 24h SLA and the vendor's 50% batch discount passes straight through to you.

Pricing classes

Free entry — activation, price queries, account metadata$0
AI inference — China 0% / Western 5%0% / 5%
Cheap ops — cron, queue, webhook, error, flag$1 / 1M ops
Heavy ops — PDF, image, captchabase + per-MB
Bandwidth — tiered, with monthly free allowance$0.05–0.10 / GB
Vendor wrap — email, SMS, storage, billing, realtime+15–25%

Install in one line, in your language

Eight GA SDKs. The infrai CLI ships inside the Python SDK.

GA
bash
pip install infrai

Compare vendor prices from your terminal:

bash
infrai price ai.chat --model auto

One install. Every language, every editor.

Eight SDKs, a CLI, and an MCP server — drop infrai into any stack or environment. Every response returns cost, latency and vendor metadata so you always know what each call did.

Eight GA SDKs + CLI

Python, TypeScript, Go, Rust, Java, C#/.NET, Ruby, PHP — same capability ids, same metadata, one line to install.

MCP server

An MCP server exposes infrai’s capabilities to any MCP-compatible environment.

Transparent metadata

cost_usd, latency_ms, vendor, cache_hit, sla_tier on every response.

Every successful call returns:

json
{
  "cost_usd": 0.0021,
  "latency_ms": 486,
  "vendor": "deepseek",
  "cache_hit": true,
  "sla_tier": "realtime"
}

Available integrations

MCP server

@infrai/mcp-server

Claude Code skill

/infrai

Cursor rules

.cursorrules

Ship your backend in two lines

Activate in two lines. 14 unified modules, Chinese AI at 0% markup, one wallet, one bill.