Inference platform for deploying AI models in production
EU-built control plane for enterprise AI that governs every LLM and MCP call
Stage
Established
Not given
Founded
2019
Not given
Based in
Not given
NL
Pricing model
Paid
Freemium
Pricing
Baseten offers three pricing tiers: Basic (pay-as-you-go starting at $0/month), Pro (with volume discounts available), and Enterprise (with custom SLAs and volume discounts). Compute pricing varies by GPU type, ranging from $0.00058/minute for CPU instances to $0.16633/minute for B200 GPUs. Model AP
Pay-as-you-go: 1M free requests per month with BYOK (bring your own keys), then 4% fee; 4.5% fee on Orq.ai keys. Included monthly: 100k spans, 1 GB processed data, 500 agent runs, unlimited AI Gateway seats. AI Studio seats €35/seat/month. Spans €7 per 100k after included allowance. Processed data €
Key features
Dedicated inference deployments
Pre-optimized model APIs
Multi-cloud deployment
Self-hosted and hybrid options
Training infrastructure with Loops SDK
Baseten Chains for compound AI
Advanced caching and decoding techniques
Baseten Embeddings Inference (BEI)
Forward-deployed engineering support
HIPAA and SOC 2 Type II compliance
OpenAI-compatible API for 500+ models from 30+ providers
MCP Gateway for governed tool calls
Budgets, spend limits and guardrail enforcement
PII detection and redaction
Agent Runtime for single and multi-agent systems
Knowledge bases with RAG and document processing
EU data residency and GDPR compliance
SOC 2 Type 2 attestation and compliance tools
Audit logs and comprehensive activity tracking
What makes it different
99.99% uptime with cross-cloud high availability
Fastest embeddings with 2x higher throughput
Pay only for compute in use, not idle time
Optimized inference stack with custom kernels and latest decoding techniques
EU-built platform with sovereignty and data residency control
Single control plane for both AI traffic and autonomous software delivery
No vendor lock-in with bring-your-own-keys and easy data export
Governance applied in real-time during execution, not after the fact
Humans remain in control of critical decisions in autonomous software delivery
Orq.ai