[ 01 / Pricing ]
Simple,
pay-as-you-go.
No subscriptions, no credit packs, no seat fees. Pay only for what you generate.
[ 01 / Rendering ]
$0.117 / min · $0.0019 / sec
Realtime passthrough (you provide audio) or async POST /v1/generate, prorated by output duration.
- GPU avatar rendering
- WebRTC video stream
- Any face image, one-shot
- Use your own STT / LLM / TTS
- React SDK & REST API
- Infinite length, no collapse
[ 02 / Interactive ]
Enterprise managed AI avatar agent, STT, LLM, TTS, and rendering. Pricing depends on your stack and volume; we onboard together.
- Everything in Rendering
- Plug in any LLM provider, or use managed providers on allowlisted deployments
- Plug in any TTS / STT provider, or use managed providers on allowlisted deployments
- Talk to your avatar instantly
- Dedicated GPU capacity on enterprise contracts
Offline / async video
$7 / hr of generated video ($0.117 / min · $0.0019 / sec). Upload a face image + audio, get a finished video back via POST /v1/generate. Same rate as realtime, billed by output duration. See API docs.
Realtime modes
Same API. Rendering is the default; Interactive is for teams we onboard together.
| Rendering | Interactive | |
|---|---|---|
| Price | $7 / hr | Custom |
| Avatar rendering (GPU) | ||
| WebRTC video stream | ||
| One-shot from a single reference image | ||
| No fixed session cap (billed by the second) | ||
| Built-in speech recognition | ||
| Built-in LLM | ||
| Built-in voice generation | ||
| Bring your own audio source | ||
| Use your own AI stack | ||
| React SDK |
[ 03 / Production & enterprise ]
When you need more than self-serve
Self-serve at $7/hr is the right answer for most teams. Production and enterprise are for teams that need reserved capacity, a specific deployment topology, or contracted support. We don't publish a fixed price for those, every workload is sized differently. Reach out and we'll quote yours.
$7 / hour
pay-as-you-go · no commitment
- Shared GPU pool
- 30 RPM basic self-serve limit
- Email support
- Pay-per-second billing
Custom
monthly or annual · high-volume throughput and concurrency
- High-volume request limits and burst quota
- Configurable retention windows
- Direct support over Slack
- Contracted response targets
Custom
annual · reserved GPU capacity
- Dedicated GPU pool · contracted capacity
- SSO via your IdP · operational logs
- DPA · sub-processor list · 99.9% SLA
- Shared Slack/Teams · named technical owner
- BYO storage · stricter retention controls
Email eric@northmodellabs.com with rough monthly volume, realtime workload shape, and any deployment constraints. We turn quotes around within one business day.
◆ Built for Enterprise
Procurement-ready, on day one.
SCIM, SSO, dedicated GPU capacity, passthrough by default, and a real audit trail. Enterprise contracts only.
SCIM / SAML SSO
Enterprise IAM via your IdP. Provision and de-provision users programmatically; no per-seat fees.
Zoom + Google Meet
Drop a NORTH avatar into a live Zoom or Meet call via standard meeting-bot frameworks (LiveKit, Recall.ai). One API request, your existing room.
Passthrough by default
NORTH receives audio and returns video. Your prompts, customer data, and knowledge base never leave your stack.
Dedicated capacity + SLA
Reserved GPU capacity, guaranteed throughput, and a 99.9% uptime SLA on Enterprise contracts.
Audit log + security review
DPA, sub-processor list, and security questionnaire support for procurement.
1 hour of generated video
Based on published API pricing. One hour of avatar video through each platform.
154×
cheaper than LongCat 720p
144×
cheaper than Hunyuan Avatar
59×
cheaper than Kling AI Pro
51×
cheaper than realtime avatar API
↓ lower is better · prices from published API docs
[ NORTH Realtime Avatar ]
Why NORTH is different
The smallest avatar model with state-of-the-art quality, running on consumer GPUs. See how NORTH compares to the largest open-source models.
See the benchmarkStart building.
Add a payment method, generate an API key, and start building with realtime avatars.