RightNow Inference Model APIs
Hosted open-model inference with OpenAI-compatible and Anthropic-compatible APIs, streaming, and session-aware routing for cached context.
Past recognitions
What it does
Hosted open-model inference with OpenAI-compatible and Anthropic-compatible APIs, streaming, and session-aware routing for cached context.
- Hosted open-model inference for agents and applications
- Connecting coding agents to open models
- Category
- Model hosting and inference
- Users
- AI agent and application builders
- Public API
- Available
Not yet disclosed: deployment options, platforms, languages and support channels.
Pricing
- Free trial$0
- Usage-based$5
- EnterpriseCustom
- Quoted by their sales team
Prices as published by RightNow, checked Nov 2026.
Security and compliance
As reported by RightNow. Ask for audit reports before you buy.
- SOC 2 Type IICompliant
- GDPRCompliant
- CCPA/CPRACompliant
- HIPAACompliant
- TLS 1.2 or higher for website and inference endpoint traffic, with HSTS preload and encrypted internal private networking.
- AES-256 encryption at rest for the primary database and object storage; provider-native encryption for cached model weights.
- Envelope encryption for API keys, OAuth tokens, and other credentials, with environment-bound secret managers.
- Email/password and Google or GitHub OAuth authentication through Supabase Auth; customer-facing SAML or OIDC SSO is not currently offered.
- Workspace-scoped role-based access control and database row-level security for tenant isolation.
- Production engineering access protected by SSO and multi-factor authentication, with least-privilege access, logging, and recurring reviews.
- Customer-data access for incident investigation is logged, scoped to relevant records, and associated with a support ticket.
- DDoS protection, private API networking, authenticated compute-provider APIs, scoped rotatable credentials, rate limiting, and bot checks.
- Mandatory code review, CodeQL scanning, GitHub secret scanning, and Dependabot alerts.
- Centralized logging, separate authentication and customer-data access logs, secret masking in application error monitoring, and continuous API health checks.
- Recurring third-party penetration testing and a continuous vulnerability management program.
- Documented incident response plan and customer breach notification without undue delay and within 72 hours of awareness.
- Hosted Model APIs advertise zero prompt retention by default and no training on prompts or completions; non-streaming responses may be cached for up to 24 hours when an Idempotency-Key is supplied.
Alternatives
Deploys AI models as callable endpoints on serverless GPUs.
RightNow Inference Model APIs vs Moonshine →Inference
by Beam
Deploy high-performance inference endpoints for serving custom models on GPU or CPU.
RightNow Inference Model APIs vs Inference →Red Hat AI Inference
by Red Hat
Optimize model performance with an integrated stack for fast, consistent, and cost-effective inference at scale.
RightNow Inference Model APIs vs Red Hat AI Inference →Model Serving
by INTELLITHING
Solution for serving models via production-grade APIs with access management and monitoring; listed as a core platform capability.
RightNow Inference Model APIs vs Model Serving →Cumulus — Production-Grade Inference Platform
by Cumulus Labs
Unified inference platform with eight subsystems: Gateway, Router, Cache, Observability, Evaluation, Fine-tune, Custom Hosting, and the Ion inference engine.
RightNow Inference Model APIs vs Cumulus — Production-Grade Inference Platform →Dedicated Model Inference
by Together AI
Deploy models on dedicated infrastructure.
RightNow Inference Model APIs vs Dedicated Model Inference →
Is this your product?
Claim it to keep details accurate and submit evidence for the next ranking review.
Claim RightNow Inference Model APIs