Inference API
An OpenAI-compatible API for hosted open and frontier models, including language, image, video, speech, and audio models, billed per use.
Past recognitions
What it does
An OpenAI-compatible API for hosted open and frontier models, including language, image, video, speech, and audio models, billed per use.
- Primary product category
- Models and AI infrastructureModel hosting and inference
- Public API
- Available
Not yet disclosed: deployment options, platforms, languages and support channels.
Pricing
- Free plan$0
- Usage-based$0.273
- /1M input tokens
Prices as published by Runcrate, checked Nov 2026.
Security and compliance
As reported by Runcrate. Ask for audit reports before you buy.
- GPU instances run in isolated containers inaccessible to other users.
- Workspace storage volumes are private and encrypted at rest.
- API keys are shown in full only once, stored securely, transmitted over HTTPS, and can be deactivated or deleted.
- Workspace roles provide Owner, Manager, and Developer access controls.
- Audit logs record significant workspace actions, including actor, timestamp, IP address, and changes.
- Payment processing is handled by Stripe, which is described as PCI DSS Level 1 certified; this is not evidence of Runcrate certification.
- Runcrate states that it uses encryption in transit and at rest, regular security audits, and strict access controls.
- Prompts and inference responses are not retained unless enabled or requested; saved playground and environment data have stated 30-day retention periods.
Alternatives
Deploys AI models as callable endpoints on serverless GPUs.
Inference API vs Moonshine →Inference
by Beam
Deploy high-performance inference endpoints for serving custom models on GPU or CPU.
Inference API 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.
Inference API 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.
Inference API 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.
Inference API vs Cumulus — Production-Grade Inference Platform →Dedicated Model Inference
by Together AI
Deploy models on dedicated infrastructure.
Inference API vs Dedicated Model Inference →
Is this your product?
Claim it to keep details accurate and submit evidence for the next ranking review.
Claim Inference API