European AI Gateway for accessing 700+ models through one API
Deploy any open model from Ollama or Hugging Face as a private, OpenAI-compatible API
Stage
Not given
Not given
Founded
2023
Not given
Based in
SE
US
Pricing model
Freemium
Paid
Pricing
Free models available at signup with no credit card required. Gateway plan: 3% platform fee on credits. Control Plane plan: 5.5% platform fee on credits plus flat-rate per-check billing for LLM checks. Token rates are provider rates with no markup. No minimums, no lock-in. Enterprise plans include v
Pay as you go: $0/month with prepaid credits from $10. Pro: $29/month with $29 monthly credits. Business: $299/month with $299 monthly credits. GPU pricing: NVIDIA L4 $0.95/hour ($0.000264/second, $1,180/month always-on); NVIDIA L40S $3.20/hour ($0.000889/second, $3,974/month always-on); 4x NVIDIA L
Key features
Access to 700+ models from 50+ providers
Spend limits and cost controls by project, role, user or key
Zero data retention by default with customizable trace storage
OpenAI SDK compatible with streaming and tool calling
Model routing with fallback options
LLM checks for flagging, redacting, blocking or scoring
Management API for infrastructure-as-code
SSO/SAML and role-based access control
JevMan Pac-Man benchmark for decision models
AI Roundtable for multi-model reasoning comparison
Deploy models with one command via CLI
OpenAI and Ollama API compatibility
Scales to zero with configurable idle timeout (60 seconds to 60 minutes)
Private endpoints with no prompt logging
Supports GGUF and safetensors model formats
Free model storage (10GB to 1TB depending on plan)
Always-on option for no cold starts
Batch jobs pricing 30-50% cheaper
What makes it different
No token markup: provider rates passed through unchanged
Zero data retention by default with flexible options
Fully OpenAI SDK compatible for easy migration
Pay-as-you-go with no minimums or lock-in
No Dockerfile or server management required
Use your existing OpenAI or Ollama client with one URL change
Pay only for actual compute seconds used, not monthly subscription
Cold start time never billed and requests wait instead of failing
Prompts and outputs never logged or used for training
Opper
BitsRun