MetriqualMETRIQUAL

Your AI stays online,even when providers don't.

Book a callSee how it works

Free to start · No card required · Cancel anytime

Your appone call, any modelMetriqualrouting · failoverOpenAIgpt-4oservingYour useranswer deliveredSub-10ms overhead · nothing dropped

Every provider.
Every modality.
One key.

2 linesto integrate
<10msrouting overhead
99.2%conversation history carried
100%of requests logged & attributable
2 liveproviders — 3 more landing
OpenAIOpenAI
ClaudeClaude
GeminiGeminiSoon
MistralMistralSoon
MiniMaxMiniMaxSoon
OpenAIOpenAI
ClaudeClaude
GeminiGeminiSoon
MistralMistralSoon
MiniMaxMiniMaxSoon
OpenAIOpenAI
ClaudeClaude
GeminiGeminiSoon
MistralMistralSoon
MiniMaxMiniMaxSoon
OpenAIOpenAI
ClaudeClaude
GeminiGeminiSoon
MistralMistralSoon
MiniMaxMiniMaxSoon
Text & Chat
Voice + Cloning
Video / Sora
Image Generation
Music Generation
Image-to-Video
Text & Chat
Voice + Cloning
Video / Sora
Image Generation
Music Generation
Image-to-Video
Reliability

Zero dropped requests, even mid-outage.

Failover reroutes every request to a healthy provider in milliseconds. A single-provider setup goes down with the provider.

Metriqual Failover active
0failed requests

The request is replayed against the next provider in the chain, carrying its conversation history. Your user sees a slower answer, never an error.

Failover overhead
1–5ms
Providers in chain
5
History carried
Yes
Single-provider setup Provider down
100%of requests fail

While the provider is down your users get an error page, not an answer. Retries hit the same endpoint, so the outage lasts as long as theirs does.

Failover
None
Providers
1
History carried
No
Research

We measured it, then published the method.

Failover that keeps the request alive but loses the conversation isn't failover. We built the benchmark for it and ran it on our own gateway.

Detectability × originLoudSilent200200
Reliability

The failures that pass every health check

Five modes across two axes. The severe ones return HTTP 200 and corrupt state.

arXiv:2607.17525
Stateful failoverStateless baseline99.2%
Benchmark

Stateful failover, measured

99.20% of context survived across 750 injected failures.

arXiv:2607.15899
layer 0final
Interpretability

How a prompt moves through a model

One three-phase structure, held across three model families.

arXiv:2606.09287
linear attentionVLA, boundedsequence length
Architecture

Long-context memory that stops decaying

State norm drops 109x at 1,000 tokens.

arXiv:2605.11196
For developers

< Change two lines.
Keep everything else. >

Swap your API key and base URL for Metriqual's. Everything else in your codebase, from prompts to parameters, stays exactly as it is.

GitHubStart integration →API reference→
metriqual — live trafficLIVE

YOUR ENTIRE MIGRATION

- api_key = "OPENAI_API_KEY"
+ api_key = "MQ_KEY"
- base_url = "https://api.openai.com/v1"
+ base_url = "https://api.metriqual.com/v1"

WHAT HAPPENS WHEN A PROVIDER FAILS

$ POST /v1/chat/completions model=gpt-4o
→ openai connect 2.00s … timeout
↻ failover next step in chain
→ anthropic claude-fable-5 · 200 OK · 412ms
✓ delivered 0 requests dropped
How it works

Three steps to an agent that stays up.

  1. Agent name
    RESEARCH_AGENT
    Model
    openai · gpt-4o
    01

    Name it, point it at a model

    Pick a provider and a model. That is the whole configuration.

  2. openai · gpt-4oprimary
    anthropic · claude-sonnet-4-5fallback
    02

    Give it a fallback

    Add a second provider. If the first one stalls, traffic moves there automatically.

  3. base_url = "api.metriqual.com/v1"
api_key  = MQ_KEY
    Live, with failover armed
    03

    Ship it

    Swap your base URL. Every request now routes through the chain you just built.

Build your first agentRead the docs
Why Metriqual

Everything the gateway does, once you are through it.

what changed in GPT-5.1 pricing?live web
GPT-5.1 pricing update[1]
openai.com
Input tokens −20%, output unchanged.
OpenAI cuts API prices again[2]
techcrunch.com
Effective this week across all tiers.
Show HN: 5.1 pricing, real invoices[3]
news.ycombinator.com
Developers compare month-over-month.

GPT-5.1 input pricing dropped ~20% this week[1]; output stayed flat[2].

Live web search

Answers from today, with the sources attached.

One flag and your agent reads the live web before it replies, then cites what it read. Works on OpenAI and Claude through the same endpoint.

"what is our refund window?"
Vector store2,172 chunks
top 4 retrievedembeddings never leave your gateway
Private knowledge

Your documents, answered from directly.

Upload what your team already wrote. It is chunked, embedded and retrieved per request, and none of it leaves your gateway on the way there.

sk-live-prodthis month
$412/ $500 cap
sk-test-eval$200 / $200
cap reachednew requests rejected
sk-live-batch
$96 / $250
Predictable costs

A key cannot spend more than you let it.

Set a cap per key. Spend is attributed in real time across every request, provider and modality, so the month never ends in a surprise.

Outbound requestraw

refund for jane@acme.io on card 4242 4242 4242 4242, phoned from +1 415 555 0132

3 entities masked before the provider saw them
PII detection

Customer data stops at your gateway.

Emails, cards and phone numbers are detected and masked in the request body before it is ever forwarded to an external provider.

support-replyv2 → v3
deployed
You are a support agent.
−Decline refunds politely.
+Decline in one line, link the refund policy.
+Always cite the doc you used.
Keep replies under three sentences.
Prompt hub

Edit the prompt without shipping the app.

Version prompts, see which one is live, and point any version at any provider. Changing a system prompt stops being a deploy.

How we compare

Everything a gateway should do, in one place.

Swipe to compare providers→
MetriqualDirect providerOther gateways
Automatic failover across providers
2-line integration (no SDK rewrite)
Conversation history carried on failover
Prompt versioning & hub
Per-agent spend controls
Multi-modal (voice, video, image, music)
Fully managed, nothing to host
Unified observability

partial / limited

Pricing

Built for every stage.

  • Unlimited agent endpoints
  • 500K requests / month
  • Per-agent spend controls
  • PII redaction
  • Webhooks + A/B routing
  • Team access (5 seats)
  • Priority support
GET STARTED
FAQ

Frequently asked questions.

Everything developers need to know before building production-ready AI agents.

Watch a provider go down.

Thirty minutes with an engineer. We kill a provider mid-conversation and you see exactly what your users would have seen.

✓ Production Ready99.99% UptimeSub-10ms Overhead