v17 live THE AI CONTROL PLANE

One API. Every model. Your rules.

Route AI requests across providers, fall back when one breaks, cap spend per key, and trace every call in real time.

Working API key in 60 seconds · BYOK-first · No credit card

requests today
uptime · 90d 99.97% 3 incidents · all routed around
providers 11connected + any OpenAI-compatible endpoint
p50 latency 312ms -12ms this week

See every routing decision.

A request enters one API, LatentKit evaluates policy, credits, provider health, key caps, and fallback state, then routes to the best eligible provider.

Everything you manage from one console.

LatentKit turns provider sprawl into product controls your team can operate.

01

Provider connections

Connect BYOK credentials, managed Platform Access, health checks, and provider priority.

02

Routing policies

Control strategy, fallback depth, response profile, route order, and publish state.

03

API keys and limits

Issue reveal-once keys with monthly caps, expirations, rotation, and instant revoke.

04

Platform credits

Separate BYOK provider billing from managed-credit usage, margin rules, and reloads.

05

Request traces

Inspect candidates, selected route, fallback chain, cost, latency, cache, and request ID.

06

Playground testing

Test chat, images, and embeddings through the same policy before production traffic.

07

Guardrails and privacy

Apply prompt controls, trace privacy settings, PII handling, and anomaly visibility.

08

Team operations

Manage roles, audit events, branded domains, white-label surfaces, and support workflows.

From signup to production traffic.

01

Start with zero setup

LatentKit prepares the default app, route, key, and quickstart path when Platform Access is enabled.

02

Choose access mode

Bring your own provider keys or use managed Platform Access where it is available for the route.

03

Shape the production policy

Set endpoint capability, response profile, fallback limit, provider order, and rollout timing.

04

Issue and test a key

Create a reveal-once app key with caps and expiration, then test the live policy in Playground.

05

Ship the base URL

Keep the OpenAI request shape and point production traffic at the LatentKit gateway.

Compare routing behavior before it ships.

Same policy, different strategy. See how priority, cost, availability, and balanced mode distribute traffic.

Click a strategy to compare traffic behavior
Your app
LatentKit
OpenAI100$0.018 / 420ms
Anthropic0$0.021 / 360ms
Gemini0$0.010 / degraded

Priority mode keeps production simple: one primary route, with the rest ready as fallback.

Edit controls without redeploying your app.

Tune response profile, eligibility, fallback depth, and canary rollout from the console while your app keeps one endpoint.

fastlow latency
balanceddefault depth
deepbest model
Anthropic / Claude SonnetBYOK primary
eligible
OpenAI / GPT-4oManaged credits
eligible
Gemini / 1.5 ProBYOK fallback
degraded

Preview

Publish v17 with priority mode, balanced response profile, OpenAI as managed fallback, and Gemini excluded while degraded.

Watch every request.

Logs, route candidates, fallback attempts, cost, latency, cache, guardrails, and request IDs.

Request trace

candidateAnthropic
selectedClaude Sonnet
fallbackarmed
Request IDreq_91af

Selected first healthy BYOK route. No guardrail match. Stored with normal trace metadata.

Drop-in OpenAI shape.

Use the official Python and JavaScript SDKs, cURL, fetch, or anything that speaks OpenAI-compatible requests.

/v1/chat /v1/vision /v1/embed /v1/image /v1/queue
from latentkit import LatentKit

with LatentKit(api_key="USE_YOUR_LATENTKIT_KEY_HERE") as client:
  response = client.chat.create(
    messages=[{"role": "user", "content": "Route this"}],
    response_profile="balanced",
  )

  print(response["content"])

Run it under your brand.

Custom domains, white-label dashboard, roles, audit logs, guardrails, and support options.

domainai.yourcompany.com
rolesadmin / operator / developer
auditpolicy publish, key rotation
identitySSO roadmap / inquiry
AAcme AI Gatewaydashboard.acme.com
Spend today$184.20
Fallback events12
Guardrail matches3

Policy v12 scheduled canary at 12%

Key lk_live_91af rotated by Tenant Admin

Custom domain certificate healthy

Start free. Scale by policy.

Compare plans →

Free

$0

Unlimited BYOK under fair use, no LatentKit usage markup, one app, one policy, and a managed trial path.

Company

Custom

Custom client workspaces, domains, branding, audit/export, governance, limits, and support.

Stop maintaining the same AI gateway twice.

Roll your own

Flexible, but every fallback, budget, trace, and provider change becomes your infrastructure.

Single-vendor proxy

Useful for one provider family, weaker when your app needs policy control across many providers.

LatentKit

One API layer for routing, provider connections, budgets, traces, credits, and team operations.

Ship AI traffic you can trust.

Connect a provider, publish a policy, ship in under 15 minutes.