Vendor profileChecked Nov 8, 2026

Modal

Modal Labs, Inc. · modal.com · Last checked:

  • Serverless GPU compute
  • Bring-your-own-model code

Company status

Active, privately held.

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Capabilities

  • Serverless containers billed per second on GPUs from T4 to B300; you supply the model and serving code
  • Documented examples for serving an OpenAI-compatible endpoint with vLLM
  • Region selection on all plans at a 1.15x to 1.75x price multiplier
  • Containers isolated with gVisor or microVMs

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Who it tends to fit

  • Engineering teams that want to run their own or fine-tuned models without managing Kubernetes
  • Teams that need custom serving code, not only a fixed model catalog

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Pricing

Published per-second GPU pricing on https://modal.com/pricing (for example, Nvidia H100 listed at $0.001097 per second); Starter plan $0 base with $30/month free credits, Team plan $250/month base.

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Published certifications

  • SOC 2 Type II
  • HIPAA (Enterprise plan)
  • GDPR (DPA available)

Listed as stated by the vendor. Scope can differ by product or subsidiary; request current reports.

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Limitations to check

  • No hosted per-token model catalog on the pages checked: you build and operate the serving stack
  • HIPAA is Enterprise-plan only, and some products are out of HIPAA scope
  • Region selection adds a price multiplier

Sources 1, 2, 3, 4, 5 · checked 2026-11-08

Sources

  1. Pricing: per-second GPU rates (H100 $0.001097/sec); Starter, Team, Enterprise plans; SOC 2 on all plans; HIPAA Enterprise only; region selection multiplier 1.15x to 1.75xmodal.com/pricingChecked 2026-11-08
  2. Security page: SOC 2 Type II report in Trust Center; DPA for GDPR; HIPAA via Enterprise plan; gVisor or microVM isolationmodal.com/docs/guide/securityChecked 2026-11-08
  3. Trust Center lists SOC 2 with SOC 2 Type 2 reportstrust.modal.comChecked 2026-11-08
  4. Example: run OpenAI-compatible LLM inference with vLLMmodal.com/docs/examples/vllm_inferenceChecked 2026-11-08
  5. Region selection guidemodal.com/docs/guide/region-selectionChecked 2026-11-08

Report a correction: [email protected]. Facts are re-checked at least every 90 days.