List your company

Inference API

Model hosting and inference · by OpenRelay

OpenAI-compatible endpoint for hosted open models including GPT-OSS 120B, GPT-OSS 20B, Gemma 4 31B, GLM 5.2, and DeepSeek-OCR 2.

Visit website

What it does

OpenAI-compatible endpoint for hosted open models including GPT-OSS 120B, GPT-OSS 20B, Gemma 4 31B, GLM 5.2, and DeepSeek-OCR 2. Supports streaming, tool calls, vision input, and JSON mode with no additional cost.

  • Production GPU inference
  • OpenAI-compatible LLM serving
  • GPU compute rental
  • Self-hosted GitHub Actions runners with GPU access
Category
Model hosting and inference
Users
Teams running AI inference workloads, ML teams needing GPU-enabled CI/CD pipelines, Developers using OpenAI-compatible LLM APIs
Public API
Available

Not yet disclosed: deployment options, platforms, languages and support channels.

Pricing

  • Usage-based$0.15
    • / $0.60 out
    • GPT-OSS 20B $0.05 / $0.20
    • GLM 5.2 $1.82 / $5.72

Prices as published by OpenRelay, checked Oct 2026.

Security and compliance

As reported by OpenRelay. Ask for audit reports before you buy.

  • SOC 2 Type IIIn progress
  • SOC 2Compliant
  • PCI DSSCompliant
  • TLS 1.3 encryption in transit
  • Encrypted volumes at rest
  • VM-level isolation with separate guest kernel
  • GPU passthrough via VFIO with IOMMU-enforced memory isolation
  • Complete GPU reset between workloads
  • WireGuard VPN tunnels for node-to-control-plane communication
  • Egress filtering
  • DDoS protection at edge proxy layer
  • HSTS enforcement
  • Zero-access architecture (providers cannot access workloads)
  • No data persistence on provider nodes by default
  • Secure wipe of workload data on termination
  • Role-based access control (Owner, Admin, Member)
  • Scoped and rotatable API keys
  • One-time use provisioning tokens with hashed storage
  • Audit logging of authentication and authorization events
  • Network segmentation and firewalls
  • Intrusion detection and monitoring
  • Regular penetration testing
  • Incident response procedures
  • Certificate pinning for control plane communications

Reviews

No reviews yet

Reviews come from people who use Inference API at work. Share how your team uses it to help other buyers decide.

Write a review

Alternatives

  • MAGIC

    by Pipeshift

    Proprietary framework (Modular Architecture for GPU Inference Clusters) that compiles workload-specific inference pipelines, controlling layers from model to silicon including K...

  • Coding Platform (Kimchi)

    by Cast AI

    Enterprise AI coding and inference platform.

  • Red Hat AI Inference

    by Red Hat

    Optimize model performance with an integrated stack for fast, consistent, and cost-effective inference at scale.

  • Inference Endpoints

    by VESSL AI

    Coming soon. OpenAI & Anthropic-compatible APIs; pay only for the tokens you use.

  • QHexRT

    by RunAnywhere, Inc.

    An inference engine designed to run LLMs, VLMs, STT, TTS, and embeddings entirely on Qualcomm Hexagon NPUs.

  • Dedicated Model Inference

    by Together AI

    Deploy models on dedicated infrastructure.

Is this your product?

Claim it to keep details accurate and submit evidence for the next ranking review.

Claim Inference API