Modular · Pricing Plans
Modular Plans Pricing
Modular Plans Pricing is the pricing profile for Modular on the APIs.io network — every figure transcribed verbatim from the provider’s own pricing page on 2026-10-07.
It defines 7 plans, including Modular Cloud — PER TOKEN OR GPU HOUR; Bring Your Own Cloud — PAY PER MINUTE; Enterprise — CUSTOM ENGAGEMENT, and 4 more.
The page prices API or platform usage directly, priced per call; the service is delivered as open-core.
Tagged areas include Company, Artificial Intelligence, Machine Learning, Inference, and LLM.
7 Plans
Prices the API
Basis: per call
Delivered: open-core
Transcribed from the provider's pricing page on 2026-10-07 — www.modular.com/pricing.
View Source
CompanyArtificial IntelligenceMachine LearningInferenceLLMGPUDeveloper ToolsInfrastructure
Plans
Modular Cloud
per-use
PER TOKEN OR GPU HOUR per token or GPU hour
Includes: Shared & Dedicated Endpoints; start by testing shared endpoints for free
Bring Your Own Cloud
per-use
PAY PER MINUTE per minute of reserved GPU capacity
Includes: Everything in Dedicated Endpoint, plus deployment in your cloud or on-premise
Enterprise
none
CUSTOM ENGAGEMENT
Includes: SOTA inference on any GPU vendor, custom kernels, community support
Self-Hosted
none
Free
Includes: Community Edition, free forever with no usage fees
DeepSeek V4 (hosted endpoint)
per-use
1.74 per $/1M input tokens
Includes: Output 3.48 per 1M; Cache Hit 0.145 per 1M
GPT OSS 120B (hosted endpoint)
per-use
0.1 per $/1M input tokens
Includes: Output 0.5 per 1M; Cache Hit N/A
FLUX.2-klein-4B (image)
per-use
1 per $/1K @ 1MP input
Includes: Output 1 per 1K @ 1MP
Sources
Work with this as data
Every plan here is available over the APIs.io API and to AI agents over MCP.