Offering overview
Developers call a REST API to run community-published or private models, and the service handles containers, scaling and GPU scheduling behind the scenes. Models are packaged with the open-source Cog format, which makes pushing a custom model as simple as defining its inputs and dependencies. Billing is per second of the hardware a prediction occupies, from small CPU slots to single and 8x NVIDIA H100 and H200 nodes, with L40S, A100 80 GB and T4 options in between. Selected language models such as DeepSeek-R1 are instead priced per token. Capacity for H200 is reserved for committed-spend contracts. The audience is product engineers and indie builders who want image, video, audio and language models in production without owning infrastructure; the company is based in San Francisco. Hardware pricing starts at $0.09 per hour ($0.000025 per second) for a small CPU slot and $0.81 per hour for an NVIDIA T4, rising to $5.49 per hour for an H100 and $43.92 per hour for an 8x H100 node.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- Model Inference, AI Applications, Fine-Tuning, Batch Processing
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- DeepSeek-R1
- 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
Not stated
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 |
|---|---|---|---|---|---|---|
| Replicate Model Hosting APINot stated | $0.81Usage Only | Unknown — RAM | Unknown | No | 7 October 2026 |
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
- replicate.com
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 7 October 2026