Pricing

Pay by the second.
Not by the call.

Feneri bills time-based. You pay for the seconds of media the engine actually processes. Every published rate is at least 4x our measured compute cost. Real-time, on-demand, GPU, and storage are priced separately.

Estimator

Cost a session in five seconds.

Drag the sliders to size your workload. We blend real-time, on-demand, GPU, and storage into a per-month estimate, the same costCents that bills you.

Estimated · monthly
$— / month · usd
Real-time inference$0
GPU bursts (peak handling)— · within plan
Storage · retention$0
Egress & webhooks$0 free
Effective rate

Unit pricing by use

Mix and match. Most teams blend real-time and on-demand depending on workload. Sovereign deployments lock in pre-paid rates.

Real-time streaminglive
$0.036
per minute of media · video + audio fused

Live face + voice on CPU. About 2 fps emotion and gaze, about one audio update per second. For agents, live calls, and games.

On-demand inferenceasync
$0.048
per minute · uploaded recording · video + audio

Async sitting: DeepFace, wav2vec, and Whisper large-v3 on a T4. Priced above realtime because the GPU path is the expensive one.

Audio-only · realtimelive
$0.018
per minute · voice affect

Voice-only path for telephony, IVR, customer ops. No vision compute. Same wav2vec pipe as the fused stream.

Audio-only · on-demandasync
$0.012
per minute · recorded audio

Call recordings, voicemail, podcast / interview analysis. Vocal affect without the Whisper GPU.

Text-onlyasync
$0.0008
per 1K tokens

Linguistic sentiment and intent. For chat, email, transcripts that arrive without media.

Dedicated GPUburst
$2.90
per GPU-hour · T4

Whisper and peak surges. Billed by the second after a 60s minimum. 4x our T4 box cost.

Report & session storagestorage
$0.04
per GB-month · metadata only

Affective state, transcripts, narrative reports. Raw video and audio are always deleted within 60 seconds.

Outbound webhooksevents
$0
free up to 1M events / mo

Threshold and transition events to your endpoint. Beyond 1M: $0.20 per 1K. Retries free.

Egressdata
$0.02
per GB · cross-region only

Free within a region. Cross-region only when you opt into multi-region replication.

Plans

Commit annually for lower unit prices and SLAs. Or stay pay-as-you-go and never touch a contract.

Free

Sandbox

Includes 60 min of real-time · 7-day window
No card required. Hard cap, no overage. Studio and MCP included.
  • 60 min real-time or 200 min on-demand
  • 1 GB storage · 30-day retention
  • One region · shared compute pool
  • Playground + Studio + MCP
  • Community support
Start free →
Developer

Build

Pay as you go · from $0.036 / realtime min · $0.048 on-demand
No monthly minimum. Pay only for what you process. Every unit is at least 4x our compute cost. Includes 10 GB storage.
  • Same unit prices as the rate card
  • 3 regions · auto-routing
  • WebSocket streaming
  • All 6 SDKs + MCP + Studio
  • Outbound webhooks · 1M free
  • Email support · 24h
Start building →
Most popular Scale

Production

Committed · from $0.034 / realtime min · on-demand stays $0.048
Annual commit holds the 4x cost floor. Whisper on-demand does not get cheaper than $0.048. GPU-hour $2.90.
  • Volume pricing that never drops below 4x cost
  • All 14 regions · auto failover
  • Pinned Whisper T4 · shorter cold start
  • 99.97% uptime SLA
  • Dedicated success manager
  • SOC 2 & ISO reports
Talk to sales →
Enterprise

Sovereign

Custom Negotiated VPC · on-prem · bring-your-own-GPU
For regulated, government, or large-scale deployments. Flat-rate or capacity-reserved, still at least 4x cost.
  • Bring-your-own-GPU or hosted
  • Custom fine-tunes on your data
  • HIPAA · PDPL · ISO 42001
  • Private VPC or on-prem
  • Named technical partner
  • 24/7 incident SLA
Get a plan →

Compare plans

FeatureSandboxBuildProductionSovereign
Unit pricing
Real-time streaming60 min free$0.036 / min$0.034 / minNegotiated ≥ 4x
On-demand inference200 min free$0.048 / min$0.048 / minNegotiated ≥ 4x
Audio-only realtimeincl.$0.018 / min$0.017 / minNegotiated ≥ 4x
Audio-only on-demandincl.$0.012 / min$0.012 / minNegotiated ≥ 4x
Text-onlyincl.$0.0008 / 1K tok$0.0008 / 1K tokNegotiated
Dedicated GPU-hour$2.90$2.90BYO or flat-rate
Storage · GB-month1 GB incl.10 GB · then $0.04100 GB · then $0.04Self-hosted or flat
Performance
Real-time latency~15 s cold~0.5 s video · ~0.8 s audio~0.5 s video · ~0.8 s audiotuned
Whisper GPUshared T4shared T4pinned T4reserved or BYO
Stream cold start~15 s~15 spinned · shortnone
Surfaces & ops
API + SDKs
MCP server
Studio (upload + live)✓ · 90s✓ · clinical✓ · clinical
Outbound webhooks1M free10M freeUnlimited
Regions1314Any
SLA99.97%99.99%
Compliance
SOC 2 / ISO 27001
HIPAA + BAA
KSA PDPL / GDPR residencyin-residence
Custom fine-tunes
Support
ChannelCommunityEmail · 24hSuccess managerNamed partner · 24/7

Questions.

Why billed by the second, not by the call?

An "inference" is a fuzzy unit. A 30-second clip and an hour-long session would both count as one call. We bill the actual seconds of media processed, so a 30-second clip is about $0.018 of real-time and an hour is $2.16. Honest, predictable, and matched to what we spend on compute.

Why does on-demand cost more than real-time?

Live face and voice run on CPU (~2 fps video, ~1 audio update per second). A sitting also runs Whisper large-v3 on a T4. That GPU minute is the expensive part, so on-demand is $0.048 and realtime is $0.036. Every published rate is at least 4x our measured Modal cost.

What counts toward storage?

Only the anonymized state metadata: numerical signals, transcripts, and narrative reports. Raw video and audio are always deleted within 60 seconds of inference, on every plan. We never bill for storing media.

Can I bring my own GPU capacity?

Yes, on Sovereign plans. We deploy the engine into your VPC (AWS, GCP, Azure, or bare metal) and bill a flat capacity license. Custom fine-tunes use your reserved capacity for training.

Do you offer non-profit or research discounts?

Yes, down to the 4x cost floor, never below it. Email research@feneri.xyz with your project.

Where can I see real-time usage?

Your dashboard shows minute-by-minute spend across every unit (real-time, on-demand, GPU, storage, webhooks), with hard caps per project and threshold alerts you set.