actaserve

Simple ways to
start building.

Use the model API at published rates. Reserve dedicated compute with a quote shaped around your workload.

Model API

Usage-based pricing

Connect through OpenAI- and Anthropic-compatible interfaces. The active model catalogue lists current rates and billing units.

  • Choose from the active model catalogue
  • Published pricing for each model
  • $5 in account credit after email verification
Get an API key View model rates

Model capabilities and pricing apply. API access does not reserve dedicated hardware or guarantee data residency.

Dedicated compute

Custom quote

Reservations open

Actaserve will own and operate the hardware. Choose root/bare-metal access or a managed API endpoint.

  • Hardware procurement, power and cooling
  • Model bring-up and ongoing operations
  • Capacity, location and access scoped per project
Reserve capacity

Dedicated capacity is reserved per contract, with the delivery date set in your quote. It is not ready-to-use inventory. Deployment terms.

Find your model. See your rate.

Published prices in USD. Token prices below are per one million tokens; other models use their listed billing unit. Check the model's supported options before sending a request.

542 models

Active public model prices in US dollars
ModelTypeInput / 1M tokensOutput / 1M tokensOther billing unit
Hunyuan3d V3fal-ai/hunyuan3d-v3/sketch-to-3d 3D Not token basedNot token based$0.015 / units
Hunyuan3d V3fal-ai/hunyuan3d-v3/text-to-3d 3D Not token basedNot token based$0.015 / units
Hunyuan Motion [0.46B]fal-ai/hunyuan-motion/fast 3D Not token basedNot token based$0.06 / generations
Hunyuan Motion [1B]fal-ai/hunyuan-motion 3D Not token basedNot token based$0.08 / generations
Hunyuan Worldfal-ai/hunyuan_world/image-to-world 3D Not token basedNot token based$0.3 / requests
Hyper3dfal-ai/hyper3d/rodin/v2 3D Not token basedNot token based$0.4 / generations
Hyper3D Rodinfal-ai/hyper3d/rodin 3D Not token basedNot token based$0.4 / generations
Hyper3D - Rodin V2.5 - Image to 3Dfal-ai/hyper3d/rodin/v2.5 3D Not token basedNot token based$0.4 / generations
Hyper3D - Rodin V2.5 - Image to 3D - Fastfal-ai/hyper3d/rodin/v2.5/fast 3D Not token basedNot token based$0.1 / generations
Hyper3D - Rodin V2.5 - Text to 3Dfal-ai/hyper3d/rodin/v2.5/text-to-3d 3D Not token basedNot token based$0.4 / generations
Hyper3D - Rodin V2.5 - Text to 3D - Fastfal-ai/hyper3d/rodin/v2.5/text-to-3d/fast 3D Not token basedNot token based$0.1 / generations
Meshy 5 Multifal-ai/meshy/v5/multi-image-to-3d 3D Not token basedNot token based$0.4 / generations
Meshy 5 Remeshfal-ai/meshy/v5/remesh 3D Not token basedNot token based$0.2 / generations
Meshy 5 Retexturefal-ai/meshy/v5/retexture 3D Not token basedNot token based$0.3 / generations
Meshy 6fal-ai/meshy/v6/image-to-3d 3D Not token basedNot token based$0.8 / generations
Meshy 6fal-ai/meshy/v6/text-to-3d 3D Not token basedNot token based$0.8 / generations
Meshy 6 - Multi Image To 3Dfal-ai/meshy/v6/multi-image-to-3d 3D Not token basedNot token based$0.4 / generations
Meshy 6 Previewfal-ai/meshy/v6-preview/image-to-3d 3D Not token basedNot token based$0.8 / generations
Meshy 6 Previewfal-ai/meshy/v6-preview/text-to-3d 3D Not token basedNot token based$0.8 / generations
Meshy 7.1 Image to 3Dmeshy/v7.1/image-to-3d 3D Not token basedNot token based$0.8 / generations

Reported cached input tokens are billed at 10% of the published input rate. Model availability can change. Read the quickstart or open the catalog API (JSON).

Bring your own model.

A dedicated-compute option, custom quoted

Deploy private weights on Actaserve-owned infrastructure, subject to model, licence and runtime qualification. Bring your checkpoint and serving requirements so we can scope model bring-up.

Reserve capacity

Ready for your first call?

Explore the docs