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.

533 models

Active public model prices in US dollars
ModelTypeInput / 1M tokensOutput / 1M tokensOther billing unit
SpaceXAI: Grok 4.5x-ai/grok-4.5 Language $2.0$6.0Token based
SpaceXAI: Grok 4.6x-ai/grok-4.6 Language $2.0$6.0Token based
SpaceXAI: Grok 4.7x-ai/grok-4.7 Language $2.0$6.0Token based
SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1 Language $1.0$2.0Token based
StepFun: Step 3.5 Flashstepfun/step-3.5-flash Language $0.1$0.3Token based
StepFun: Step 3.7 Flashstepfun/step-3.7-flash Language $0.2$1.15Token based
StepFun: Step 5 Previewstepfun/step-5-preview Language $1.0$2.7Token based
Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct Language $0.14$0.57Token based
Tencent: Hy3tencent/hy3 Language $0.132$0.528Token based
Tencent: Hy3 previewtencent/hy3-preview Language $0.18$0.6Token based
Tencent: Hy4 previewtencent/hy4-preview Language $0.834$2.501Token based
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b Language $0.044$0.177Token based
Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b Language $0.074$0.295Token based
Tencent: Hy-MT2-7Btencent/hy-mt2-7b Language $0.074$0.295Token based
TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1 Language $0.3$0.5Token based
TheDrummer: Skyfall 36B V2thedrummer/skyfall-36b-v2 Language $0.55$0.8Token based
TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b Language $0.4$0.4Token based
Thinking Machines: Inklingthinkingmachines/inkling Language $1.0$4.05Token based
Thinking Machines: Inkling (free)thinkingmachines/inkling:free Language $0.0$0.0Token based
Thinking Machines: Inkling Smallthinkingmachines/inkling-small Language $0.45$1.2Token based

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