Akamai Cloud GPU Instances & Akamai Inference Cloud
Hyperscaler cloud
Provided by Akamai Technologies, Inc.
Offering overview
Akamai folded the former Linode platform into a globally distributed cloud and now positions it for inference workloads that benefit from proximity to users. GPU compute plans come in three families: NVIDIA RTX 4000 Ada (20 GB, 1 to 4 cards), NVIDIA Quadro RTX 6000 (24 GB, limited availability), and the newer RTX PRO 6000 Blackwell Server Edition with 96 GB per card in 1 to 8 card plans. Blackwell plans are offered in roughly twenty cities across North America, Europe, and Asia-Pacific, while the Ada and Quadro options are limited to a handful of regions. The Akamai Inference Cloud brand ties these instances to the company's 4,400+ points of presence and security stack, targeting real-time model serving, media transcoding, and computer-vision applications rather than large-scale training. Egress is priced at roughly $0.005 per GB in most regions, which the company highlights as a major cost advantage for data-heavy AI apps. Hourly billing with no commitment is standard: the smallest RTX 4000 Ada plan lists at $0.52 per hour, a Quadro RTX 6000 plan at $1.50, and a single RTX PRO 6000 Blackwell instance at $3.00 per hour in North America.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- Model Inference, Edge Inference, AI Applications, Batch Processing, Fine-Tuning
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- Not stated
- 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
Netherlands, Europe · India, Asia · Italy, Europe · Canada, North America · Japan, Asia · Sweden, Europe · United Kingdom, Europe · Germany, Europe · France, Europe · Spain, Europe · Indonesia, Asia · Singapore, Asia · United States, North America
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 |
|---|---|---|---|---|---|---|
| Akamai Cloud GPU Instances & Akamai Inference CloudNot stated | $0.52Usage Only | Unknown — RAM | Unknown | No | 7 October 2026 |
Questions & answers
- Which GPU families does Akamai Cloud offer?
- GPU plans include NVIDIA RTX 4000 Ada with 20 GB per card, Quadro RTX 6000 with 24 GB, and RTX PRO 6000 Blackwell Server Edition with 96 GB. Quadro availability is limited.
- What workloads does Akamai Inference Cloud target?
- It targets real-time model serving, media transcoding and computer-vision applications rather than large-scale training.
- Where are Akamai GPU instances offered?
- Blackwell plans are offered in roughly twenty cities across North America, Europe and Asia-Pacific. Ada and Quadro options are limited to a handful of regions.
- How are GPU instances billed?
- Hourly billing with no commitment is standard.
- How does Akamai Inference Cloud relate to its wider network?
- Akamai Inference Cloud ties GPU instances to the company's more than 4,400 points of presence and its security stack.
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
- akamai.com
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 18 October 2026