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
Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct Language $2.0$6.0Token based
Mistral: Sabamistralai/mistral-saba Language $0.2$0.6Token based
Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507 Language $0.1$0.3Token based
MoonshotAI: Kimi K2 0711moonshotai/kimi-k2 Language $0.57$2.3Token based
MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905 Language $0.6$2.5Token based
MoonshotAI: Kimi K2.5moonshotai/kimi-k2.5 Language $0.5$2.5Token based
MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6 Language $0.65$3.41Token based
MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code Language $0.6712$3.35Token based
MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking Language $0.6$2.5Token based
MoonshotAI: Kimi K3moonshotai/kimi-k3 Language $0.8$15.0Token based
MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batch Language $2.28$11.4Token based
Morph: Morph V3 Fastmorph/morph-v3-fast Language $0.8$1.2Token based
Morph: Morph V3 Largemorph/morph-v3-large Language $0.9$1.9Token based
MythoMax 13Bgryphe/mythomax-l2-13b Language $0.08$0.11Token based
Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-mini Language $0.025$0.1Token based
Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-pro Language $0.075$0.25Token based
Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b Language $1.0$1.0Token based
Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b Language $0.7$0.7Token based
Nous: Hermes 4 405Bnousresearch/hermes-4-405b Language $1.0$3.0Token based
NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety Language $0.2$0.2Token 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