Requesty: AI Gateway & LLM Router for 600+ Models
The AI Gateway for Production
Access 600+ models through one API with routing and failover, spend limits, governance and full observability of every request.
Get started freeSpeak to founders
Or email us atsales@requesty.ai
app.requesty.ai/analytics
R
Requesty
Balance
+ Top Up
$4,182.14
OBSERVABILITY
Analytics
Leaderboard
Logs
Audit Logs
AI GATEWAY
Model Library
Model Discovery
MCP Gateway
CONFIGURATIONS
Prompt Library
API Keys
Routing Policies
Bring Your Own Keys
My Groups
ADMIN
Admin Panel
Settings
T
Thibault Jaigu
Model Usage 5 models
| Model | Requests | Tokens | Cost | Avg Latency | | --- | --- | --- | --- | --- | | opus-5 | 42,180(34.2%) | 18.4M(38.0%) | $163.15 | 892ms | | gpt-5.6-sol | 31,420(25.5%) | 12.8M(26.4%) | $114.70 | 445ms | | gemini-3.7-flash | 24,100(19.6%) | 9.6M(19.8%) | $81.20 | 512ms | | deepseek-v4-flash | 15,600(12.7%) | 5.2M(10.7%) | $52.90 | 380ms | | glm-5.3 | 9,900(8.0%) | 2.4M(5.0%) | $34.00 | 310ms |
Filters
Group:model
Metric:cost
Calc:sum
Time:7d
Group:day
Reset
Refresh
Sum of Cost by Model Over Time$445.95
opus-5
gpt-5.6-sol
gemini-3.7-flash
deepseek-v4-flash
glm-5.3
Data Summary 5 series
Export CSV
| Model | Total | Feb 24 | Feb 25 | Feb 26 | Feb 27 | Feb 28 | Mar 1 | Mar 2 | Mar 3 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | opus-5 | $163.15 | $18.40 | $20.15 | $22.30 | $19.80 | $21.45 | $23.20 | $17.75 | $20.10 | | gpt-5.6-sol | $114.70 | $12.50 | $13.20 | $15.80 | $14.20 | $14.80 | $16.40 | $12.80 | $15.00 | | gemini-3.7-flash | $81.20 | $8.30 | $9.40 | $11.20 | $10.80 | $10.20 | $11.60 | $9.20 | $10.50 | | deepseek-v4-flash | $52.90 | $5.80 | $5.90 | $7.40 | $6.50 | $7.20 | $7.00 | $6.10 | $7.00 | | glm-5.3 | $34.00 | $3.20 | $3.50 | $4.60 | $4.50 | $4.80 | $5.00 | $3.90 | $4.50 |
Active Groups
5
84 members
Active Policies
18
all enforced
PII Redactions Today
247
100% scrubbed
Budget Utilization
67.4%
$14,518 / $21,500
Groups & Policies 5 groups
+ New Group
| Group | Members | Spending Limit | PII Redaction | Guardrails | Models | Region | | --- | --- | --- | --- | --- | --- | --- | | Engineering | 24 | $3,241/ $5,000 | ON | strict | 12 models | EU | | Marketing | 8 | $892/ $1,500 | ON | standard | 5 models | EU | | Research | 15 | $7,820/ $10,000 | ON | permissive | All | EU + US | | Customer Support | 32 | $1,445/ $2,000 | ON | strict | 3 models | EU | | Executive | 5 | $1,120/ $3,000 | ON | standard | 8 models | EU |
Global Policies ALL ENFORCED
PII Auto-Redaction
EU Data Residency
Secrets Masking
Spending Alerts
Entra Directory Sync
Model Allowlisting
Audit Logging
Zero Data Retention
Trusted by teams at
600+
Models
99.25%
Success with fallback policies
4
Regional gateways
225B+
Tokens/day
Your AI ops, at a glance
Heatmaps, cost breakdowns, cache gauges across all your AI providers.
Total Requests
143.2K
+18.7%vs last month
Across all providers and models. Peak: 8.2K/hr at 14:00 UTC.
Total Cost
$1,247
-12.3%vs last month
Down from $1,422 last month thanks to auto caching and a cheaper model on two routes.
Cache Hit Rate
78.6%
+4.2%vs last month
111.8K cache hits saved $978 this month. Auto caching enabled.
Uptime
99.97%
30 days
Auto-failover triggered 3 times. Zero downtime for your users.
Cache Performance
78.6%
Hit Rate
111.8K
Hits
30.4K
Misses
$978
Saved
By Model
opus-5
$426 34.2%
gpt-5.6-sol
$318 25.5%
gemini-3.7-flash
$244 19.6%
deepseek-v4-flash
$159 12.7%
glm-5.3
$100 8%
Total 143.2K requests$1,247
Plug & Play
Integrate in
a minute
Integrate Requesty in just 3 lines of code. No changes to your existing stack. Use the OpenAI SDK you already know.
OpenAI-compatible API, works with any SDK
No vendor lock-in. Switch models with one line
Automatic failover & load balancing included
Routing
Route every request
Fail over, load balance or route by latency across 600+ models, and choose the region with the base URL. No retry logic in your app.
Spend Management
See where the money goes, then cap it
Hard limits per key, user, team and organization, alerts before a limit hits or a key leaks, and every dollar attributed to the model, team and customer that spent it.
Governance
Define and enforce the rules
Decide which models and regions each team can use, mask PII before it reaches a provider, hand auditors the evidence, and sync your teams from Entra.
Observability
Every request, traced and attributed
Logs and traces for every call, sessions stitched back together, and usage tagged to the user, end customer or pull request it served.
See observability and analytics
Customers
See it in production
Three different reasons to put a gateway in front of your models: scale, sovereignty, and growing across 13 providers on one integration.
Review and residency
Built to survive procurement
The questions security and legal ask, answered before they ask them.
Type I held
SOC 2 Type I, Type II under audit
We hold SOC 2 Type I and are in the audit period for Type II. Controls are in place and documented; status is on thetrust page.
Contractual
GDPR, DPA on request
An Article 28 DPA, signed on request at any spend, withsub-processors listed.
Regional
EU residency
Frankfurt, on AWS eu-central-1, via router.eu.requesty.ai.
Retention
Zero data retention, enforced
Require zero data retention models for the whole organization, and anything else is refused. 131 of the EU model endpoints qualify.
Pricing
One number, and it sits on top of the model cost
No per-seat pricing, no minimum spend. You pay for what your application spends, plus 5%.
Pay as you go
5%markup on model cost
Routing, failover, caching, spend limits, alerts and analytics on every plan. Guardrails are billed per token scanned. No seat fees.
0%
Bring your own keys
on your own provider contracts
Keep the pricing you have negotiated with each provider and still get routing, limits and observability across all of them.
Volume
Enterprise
discounts and committed spend
SSO with Entra or Okta directory sync, groups, role scoped logs, guardrails included, a DPA on request and a named contact.
Questions & Answers
Start building with Requesty
One line of code. 600+ models. Full control.