Northflank Runtime Platform
Model hosting & serving platform
Provided by Northflank Ltd
Offering overview
Teams that want a Heroku-like workflow but with GPUs and bring-your-own-cloud control are the target audience for this London-based platform. Git-connected builds, preview environments, CI/CD, secrets, backups and rollbacks sit on top of secure microVMs, and the same control plane can drive Northflank Cloud or any imported Kubernetes cluster (EKS, GKE, AKS, OpenShift, Rancher, bare metal). AI-specific capabilities include one-click deployment of open models such as Llama 4 and DeepSeek, autoscaled inference services, long-running agents using MCP, RAG and multimodal tools, Jupyter notebooks, pgvector-backed Postgres, fractional and spot GPUs, and sandboxed code execution for generated code. Training jobs run as scheduled or batch workloads. On Northflank Cloud, pay-as-you-go GPU rates start at $0.80 per hour for an NVIDIA L4 24GB, rising to $1.76 for A100 80GB, $2.74 for H100 80GB and $3.00 for RTX PRO 6000 96GB; CPU is $0.01667 per vCPU-hour. Running in your own VPC adds no platform fee on the pay-as-you-go tier, with custom enterprise pricing above that. SOC 2 Type 2 and HIPAA compliance are listed.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- AI Applications, AI Agents, Model Inference, Model Training, Fine-Tuning, Batch Processing, Vector Search
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- Llama 4, DeepSeek
- AI frameworks
- Not stated
- Inference endpoints
- Unknown
- Fine-tuning
- Unknown
- Vector database
- Unknown
- Model catalog
- Unknown
- Monitoring
- Not stated
- Evaluation
- Not stated
Security & compliance
No controls are stated.
Geography
Provider headquarters are separate from offering infrastructure and availability.
Infrastructure regions
Global
Data-residency jurisdictions
Not stated
Service availability
Not stated
Support coverage
Not stated
Available plans
Pricing can change. Promotional prices are shown separately from standard prices.
| Plan | Price | Compute | Storage | GPU | Price checked | Actions |
|---|---|---|---|---|---|---|
| Northflank Runtime PlatformNot stated | $0.80Usage Only | Unknown — RAM | Unknown | No | 7 October 2026 |
Questions & answers
- Where can Northflank deploy workloads?
- Northflank can deploy on Northflank Cloud or imported Kubernetes clusters, including EKS, GKE, AKS, OpenShift, Rancher and bare metal. It supports customer environments on AWS, GCP, Azure and on-premises.
- Which AI workloads does Northflank support?
- Northflank supports autoscaled inference, long-running agents using MCP, RAG and multimodal tools, Jupyter notebooks and sandboxed execution of generated code. Training jobs can run as scheduled or batch workloads.
- What development workflow features are included?
- Northflank provides Git-connected builds, preview environments, CI/CD, secrets, backups and rollbacks.
- Does Northflank support model deployment and vector storage?
- Northflank provides one-click deployment of open models such as Llama 4 and DeepSeek, along with pgvector-backed Postgres for vector storage.
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Unverified
- Primary source
- northflank.com
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 18 October 2026