Related: shares the task Running models yourself
Inference cloud offering model APIs, private deployments and GPU resources.
Paid
Use cases
- Serving AI models to applications
- Deployment of production inference endpoints
Pricing: Pricing depends on the model: supported language models use token billing while other workloads may use execution-time billing. Private model deployments and GPU rental are distinct from shared inference API rates; there is no single monthly price for all models.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-11-03.
Related: shares the task Running models yourself
AI cloud unifying hosted model APIs, GPU infrastructure and isolated agent sandboxes.
Paid
Use cases
- Serving AI models to applications
- Deployment of production inference endpoints
Pricing: Model APIs are metered by model-specific input, output and cached-token rates. GPU Cloud and Agent Sandbox have separate resource pricing; verify account credit and the chosen product’s rate rather than treating all services as one subscription.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-11-03.
Related: shares the task Running models yourself
Multi-framework inference server, formerly Triton Inference Server, for deploying models on GPUs and CPUs.
Open (open weights/source)
Use cases
- Serving AI models to applications
- Deployment of production inference endpoints
Pricing: The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.
Documentation ↗ · Sources
This record was last reviewed on 2026-11-03.
Related: shares the task Running models yourself
Containerized inference microservices for deploying pretrained and customized models on NVIDIA infrastructure.
Freemium
Use cases
- Serving AI models to applications
- Deployment of production inference endpoints
Pricing: Developer Program access covers NIM endpoints and containers for development and testing. Production security updates and support are associated with NVIDIA AI Enterprise or partner endpoints; GPU infrastructure and model-specific terms remain separate from prototype access.
Documentation ↗ · Sources
This record was last reviewed on 2026-11-03.
Related: shares the task Running models yourself
SambaNova’s hosted inference service, now branded SambaCloud, with OpenAI-compatible requests.
Freemium
Use cases
- Serving AI models to applications
- Deployment of production inference endpoints
Pricing: SambaCloud separates developer access, production pay-as-you-go and larger subscription-based plans. Rates and rate limits depend on the selected model and plan; API usage is not included merely by installing an OpenAI-compatible client.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-11-03.
Related: shares the task Running models yourself
German AI company that builds sovereign large language models and enterprise AI platforms for industry, public-sector, and defense customers.
Paid
Use cases
- Public-sector and defense applications that require data to stay in Europe
- Enterprise assistants in industry, administration, and science
- Research collaborations on transparent language models
Pricing: Aleph Alpha sells to organizations rather than consumers and does not publish list prices; commercial terms are arranged directly with enterprise and public-sector customers.
Documentation ↗ · Sources
This record was last reviewed on 2026-09-10.
Related: shares the task Running models yourself
Managed AWS service for building applications with foundation models from multiple providers via one API.
Paid
Use cases
- Enterprise apps that need a choice of models under one API
- RAG systems grounded in private company data
- Regulated workloads requiring AWS data controls
Pricing: Pricing is usage-based per input/output token, with on-demand and provisioned-throughput options.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-10-09.
Related: shares the task Running models yourself
AWS portfolio of Amazon-built foundation models and services for text, multimodal, speech, custom model building, and UI-automating agents.
Paid
Use cases
- Cost-sensitive chat, summarization, and multimodal analysis on AWS
- Building a custom frontier model with Nova Forge
- Automating production UI workflows with Nova Act agents
Pricing: Amazon Nova is billed through AWS, typically via Amazon Bedrock, with usage-based pricing that varies by model and service.
Pricing ↗ · Documentation ↗ · Sources
This record was last reviewed on 2026-09-04.