The AI gateway
that lowers your token bill.
Buy inference for every major model through one API. Set policies like ZDR and spend limits once. We manage the providers and failover, and our optimizer finds cheaper models to save you money.
Need HIPAA-compliant endpoints and BAAs?- Processing trillions of tokens a month
- SOC 2 Type II
- HIPAA compliant
- No fees
What you get from Concentrate's managed AI gateway.
Pooled rates, no provider commitments
We pool usage across all our customers and hold the provider commitments ourselves. Volume rates come as you grow, without signing one.
Control coding spend
Per-developer keys, daily caps, and unusual-spend alerts. Stop a runaway agent before it hits the bill.
Move to open models
Our model optimizer tests GLM, DeepSeek, Qwen, and Kimi on your real requests, so you see the savings before you switch.
HIPAA with one BAA
Sign one BAA with us instead of one per provider. Fewer contracts and fewer security reviews.
Visibility and governance
See spend and usage in real time. Set limits by team or key. SOC 2 Type II, ZDR, SSO, RBAC, and audit logs.
Nothing to host
We run the gateway, provider capacity, and failover. No servers, no proxy to patch, no inference to buy elsewhere.
Built for teams that are crushing tokens.
Concentrate is an AI gateway and model router for coding agents, internal workflows, and customer-facing products, with the governance that fintech, insurtech, and healthcare teams need, and any company that processes sensitive data.
- Markup on tokens
- None
- Infrastructure you run
- None
- Cloud or framework lock-in
- None
We supply the inference
Buy tokens for every model through Concentrate. No contract with each lab, and no commitment to any single one.
Nothing to host or patch
Concentrate is fully managed. There is no proxy to deploy, no database to run, and no upgrade to schedule.
Bulk pricing as you grow
We pool usage across customers and hold the provider commitments ourselves, so your rates improve as your spend grows.
How to use Concentrate
- STEP 01
Create your workspace and add teams.
WorkspaceWorkspacePersonalTeamSupport - STEP 02
Purchase tokens
Use credits on any model or provider. No service fee or credit card fees.
Balance$99.00Used today$10.42 - STEP 03
Swap your base URL
. Point your client at Concentrate. Pick the model you want.
API keybase_url = "https://api.concentrate.ai/v1" - STEP 04
Deploy and govern
Add spend controls, review logs, and adjust as you grow.
ControlsSpend limit$500/keyAccessTeam RBACAudit logsOn
Enterprise ready
Enterprise-grade features for teams of any size
The access controls, spend visibility, and data rules you expect from an LLM gateway, from your first key to your largest team.
Access and keys
Universal API Keys
Issue keys without sharing provider-console access.
BYOK
Store your provider keys. Burn through credits or committed spend.
Team Workspaces
Map teams, projects, and keys to the right owners.
RBAC
Control who can manage members, teams, keys, and settings.
SSO / SAML
Require SSO, verify domains, and connect your identity provider.
Spend and visibility
Data and uptime
Fallbacks
Follow the provider chain you set when one slows down or fails.
Data Redaction
Redact sensitive PII, PCI, and PHI from prompts, responses, or both.
ZDR
Turn zero data retention on and enforce it by provider, team, or key.
HIPAA LLM Gateway
Run healthcare workloads on BAA-covered routes, with zero data retention locked on.
Frequently asked questions (FAQs)
What is Concentrate.ai?
What is an AI gateway?
Is Concentrate a model router?
Do I need accounts or keys with each provider?
How does pricing work?
How can we lower model spend?
How is Concentrate different from OpenRouter?
How is Concentrate different from Vercel AI Gateway?
How is Concentrate different from LiteLLM?
How is Concentrate different from Portkey?
Is Concentrate built for regulated industries?
Can we use Concentrate for HIPAA workloads?
Use any model in under 30 seconds.
Create a key, point your client at Concentrate, and pick a model. Your existing OpenAI or Anthropic SDK code keeps working.
base_url = "https://api.concentrate.ai/v1"