Every request, passed right.

One API key for 40+ providers and 200+ models. PassingRight sends each call to the model that fits it, then shows you what it cost.

Get an API keyRead the quickstart

Free with your own provider keys and no card to add. Works with the OpenAI SDK you already use: change the base URL and keep your code.

Moving fromGitHub Copilot🚅LiteLLMOpenRouterall guides

POST /v1/chat/completions

“Refactor this React hook and add tests.”

model: auto · 2,140 input tokens · tool calls

Passed to0.9 s

claude-sonnet-4-6

Anthropic

Best coding score under your budget

billed $0.0038

POST /v1/chat/completions

“Turn these bullet points into a two-line summary.”

model: auto · 310 input tokens

Passed to0.4 s

gpt-5.2-mini

OpenAI

Cheapest model that clears the quality floor

billed $0.0002

POST /v1/chat/completions

“Extract every deadline from this 80-page contract.”

model: auto · 96,000 input tokens · PDF

Passed to3.1 s

gemini-2.5-flash

Google

Only fit that fits the context window at this price

billed $0.0110

Three real requests, one key. The model on each ticket is chosen per call from price, speed and quality, and you can pin one whenever you want.

Routes across 40+ providers, including

View all providers

Integration

Drop-in compatible.
Zero learning curve.

Already using OpenAI's SDK? Change one line—your base URL—and you're done. Works with any language or framework.

  • Works with OpenAI, Anthropic, and Vercel AI SDKs
  • Change one line — your base URL
  • Every request tracked with cost, latency, and token usage
Python
import openai

client = openai.OpenAI(
    api_key="YOUR_LLM_GATEWAY_API_KEY",
    base_url="https://api.passingright.io/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, how are you?"}]
)
print(response.choices[0].message.content)

Platform Capabilities

Everything you need to
ship with confidence

Unified API Interface

Keep your existing OpenAI SDK code—just change the base URL and you're live.

Learn more

Multi-provider Support

Access 40+ providers through one integration—no vendor lock-in, switch models instantly.

Learn more

Performance Monitoring

Compare latency, cost, and quality across models to pick the best fit for each use case.

Learn more

Secure Key Management

One dashboard for all your provider keys—no more scattered credentials or exposed secrets.

Learn more

Cost-aware analytics

See requests, tokens, total spend, and average cost per 1K tokens across 7 or 30 days.

Learn more

Per-model/provider breakdown

Break down usage and spend by provider and model so you can quickly spot expensive outliers.

Learn more

Errors & reliability monitoring

Monitor error rate, cache hit rate, and reliability trends directly from the dashboard.

Learn more

Project-level usage explorer

Drill into each project's requests, models, errors, cache, and costs with dedicated charts and tables.

Learn more

Enterprise Audit Logs

Track who did what, when, and maintain compliance with comprehensive audit trails.

Learn more

LLM Guardrails

Prevent prompt injection, detect PII, and block malicious requests with intelligent guardrails.

Learn more

How It Works

One request. Any model.

Your app sends one request. We route it to OpenAI, Anthropic, Google, or any of 40+ providers—automatically picking the best path.

40+
Providers
200+
Models
100B+
Tokens routed
View all modelsRequest Model

Pricing

Two ways to pay. One of them is free.

No seats, no minimums, no token markup. Start free and only pay when you top up credits.

Credits

5% flat fee

Pay-as-you-go credits for any model at provider rates, with a flat platform fee on top-ups. No subscription, no markup on tokens.

Bring your own keys

Free

Route through your own provider API keys and pay providers directly. Routing, tracking, and analytics included at no cost.

Compare all plans, including Enterprise
RELIABILITY

Never go down. Even when your providers do.

PassingRight automatically routes requests to healthy providers in real-time. When one goes down, your traffic seamlessly fails over—your users never notice.

WITHOUT LLM GATEWAY
94%
uptime per provider
~22 days
of downtime per year
WITH LLM GATEWAY
94%
combined uptime across providers
<32 seconds
of downtime per year

Each provider averages ~94% uptime independently. With automatic failover across multiple providers, the probability of simultaneous downtime drops to near zero—giving you effective uptime of 99.9999%.

FAQ

Common questions

Everything you need to know about pricing, models, and getting started.

Can't find an answer? Contact us

Unlike OpenRouter, we offer:

  • Per-request routing that picks the model by price, speed and quality
  • Deeper, real-time cost & latency analytics for every request
  • Bring Your Own Keys – use your own provider API keys for free
  • Flexible enterprise add-ons (dedicated shard, custom SLAs)

Start routing requests
in 30 seconds

Join the developers routing their AI traffic through PassingRight. Free tier included, no credit card required.

Read the quickstart