Learn about billing and pricing for AI Real-time Interaction, including Agent Service fees, ARTC fees, and optional add-ons.
Purchase
To use AI Real-time Interaction:
Ensure AI Real-time Interaction is activated. If not, go to Activate Service.
NoteThe message "The quantity you are purchasing exceeds the available limit. Please select a new quantity!" indicates the service is already activated.
Product pricing
Standard pricing for Agent Service
Audio-only agents are billed at audio specifications. Standard audio pricing covers Speech-to-Text (STT), Text-to-Speech (TTS), and agent runtime.
Agents with video input or output are billed at video specifications. Standard video pricing covers STT, TTS, and agent runtime (excluding digital human).
The standard pricing model bundles all three services into one price.
Specification/region | Chinese mainland (USD/minute) | Singapore (USD/minute) |
Audio | 0.014 | 0.028 |
Video | 0.0502 | 0.1003 |
ARTC pricing
ARTC charges by call duration at a globally uniform rate. Full pricing in ARTC Fees.
Latency statistics are enabled by default, so voice calls incur ARTC fees at 480p resolution. To disable, contact Alibaba Cloud support.
Digital human (optional)
AI Real-time Interaction supports FaceUnity and Lingjing digital human integrations.
FaceUnity: Contact FaceUnity for pricing details.
Lingjing: Submit a ticket to activate this service.
Large language model (LLM) (optional)
The system preset LLM is currently free.
Using a non-preset LLM incurs separate fees per that product's billing documentation.
Billing rules
Total AI Real-time Interaction fee = Agent Service fee + ARTC service fee
Fee for each service = Unit price of the service × Billable duration
Billing cycle: Fees settle hourly, typically within 30 minutes after a session ends. Durations round up to the next full minute.
Billing example
User A makes 10 audio-only calls with an AI agent in the Chinese mainland region, each lasting 2 minutes:
Agent Service fee: The billable duration is 20 minutes (10 calls × 2 minutes). The cost is USD 0.28 (20 minutes × USD 0.014/minute).
ARTC: Because the calls are two-way, the billable duration is 40 minutes (10 calls × 2 minutes × 2). The cost is USD 0.0344 (40 minutes × USD 0.00086/minute).
Total cost: USD 0.3144 = USD 0.28 + USD 0.0344.