You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: fern/pricing.mdx
+28-1Lines changed: 28 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -70,7 +70,7 @@ For large-scale deployments, we offer:
70
70
</Accordion>
71
71
72
72
<Accordiontitle="How is billing calculated?">
73
-
Billing is calculated based on actual usage - voice minutes, API calls, and storage used. You can monitor usage in real-time in your dashboard.
73
+
Billing is calculated from usage across Vapi platform fees and provider passthrough costs (for example, transcriber, model, voice, and telephony). Some provider pricing is per stream, so dual-stream configurations can cost more than single-stream configurations. You can monitor usage in real-time in your dashboard.
74
74
</Accordion>
75
75
76
76
<Accordiontitle="Can I change plans anytime?">
@@ -112,6 +112,33 @@ For large-scale deployments, we offer:
112
112
</Card>
113
113
</CardGroup>
114
114
115
+
### Azure STT pricing clarification
116
+
117
+
Azure’s published real-time Speech-to-Text base price is typically around **$1.00/hour** (about **$0.0167/min**) **per stream**.
118
+
119
+
If you see **$0.016/min** in examples, treat it as a **single-stream reference rate**, not the default total for dual-stream calls.
120
+
121
+
By default, Vapi transcribes **two streams** for many voice pipelines:
122
+
123
+
-**Customer audio stream**
124
+
-**Assistant audio stream**
125
+
126
+
Because both streams are sent to Azure STT, the effective rate is typically about:
127
+
128
+
-**$0.033/min total STT** (2 × $0.0167/min), before any regional/provider-specific differences
129
+
130
+
<Note>
131
+
For streaming STT, Azure bills based on audio sent to the service. In continuous streaming, silence and pauses are still part of the streamed audio, so your billed minutes usually track stream duration.
132
+
</Note>
133
+
134
+
To reduce Azure STT cost toward single-stream pricing:
135
+
136
+
- Enable **`modelOutputInMessagesEnabled: true`** to skip assistant-channel retranscription when supported.
137
+
- This optimization currently requires **ElevenLabs voice** (word-level timestamps are needed for interruption handling).
138
+
- If you use other voice providers, the assistant stream may still be transcribed.
139
+
140
+
If you use **BYOK (your own Azure credentials)**, Vapi does not charge Azure STT passthrough on your behalf; Azure bills you directly in your own account.
141
+
115
142
### Starter Credits
116
143
117
144
Every new account is granted **$10 in free credits** to begin testing voice workflows. You can [begin using Vapi](/quickstart/phone) without a credit card.
0 commit comments