Provider Pricing
Reference pricing for STT, LLM, and TTS providers used with HMS Sovereign.
Last updated: September 2026
All prices in USD. These are the API costs charged by providers - not HMS Sovereign pricing to customers.
The Google Cloud (EU) entries below are the exception to "bring your own key": they run on the platform's own Google Cloud service account in the EU, there is no key to enter and no BYOK variant, and the usage is passed through at cost like every other provider on platform keys.
Speech-to-Text (STT)
Deepgram
| Model | Price per Minute |
|---|---|
| Nova 3 (Multilingual) | $0.0092 |
| Nova 3 (Monolingual) | $0.0077 |
| Nova 2 | $0.0058 |
| Nova 1 | $0.0058 |
| Enhanced | $0.0165 |
| Base | $0.0145 |
Note: Prices are Pay-As-You-Go tier. Growth tier is ~17% cheaper.
Gladia
| Model | Price per Hour |
|---|---|
| Solaria (Async) | $0.61 |
| Solaria (Real-time) | $0.75 |
Converted to per minute: ~$0.0102/min (async), ~$0.0125/min (real-time)
Mistral (Voxtral)
| Model | Price per Minute |
|---|---|
Voxtral Mini Transcribe (voxtral-mini-latest) | $0.003 |
Voxtral Realtime (voxtral-mini-transcribe-realtime-2602) | $0.006 |
Google Cloud Speech (EU)
Google Cloud Speech-to-Text v2 with the Chirp 3 model, served from Google's EU location (eu) on the platform's service account. Select it with stt_config.provider: google; there is no key to enter. Streaming recognition is billed per minute of audio.
| Model | Price per Minute (streaming) |
|---|---|
Chirp 3 (chirp_3) | $0.016 |
Language Models (LLM)
OpenAI
Prices per 1M tokens.
| Model | Input | Output |
|---|---|---|
| GPT-5 Mini | $0.25 | $2.00 |
| GPT-4.1 | $2.00 | $8.00 |
| GPT-4.1 Mini | $0.40 | $1.60 |
| GPT-4.1 Nano | $0.10 | $0.40 |
| GPT-4o | $2.50 | $10.00 |
| GPT-4o (2024-05-13) | $5.00 | $15.00 |
| GPT-4o Mini | $0.15 | $0.60 |
| GPT-4 Turbo | $10.00 | $30.00 |
| GPT-4 | $30.00 | $60.00 |
| GPT-4 32K | $60.00 | $120.00 |
| GPT-3.5 Turbo | $0.50 | $1.50 |
| GPT-3.5 Turbo 16K | $3.00 | $4.00 |
Recommended for voice assistants: GPT-5 Mini (best value), GPT-4o Mini (fastest), GPT-4.1 Mini (balanced)
Live API (full-duplex speech-to-speech):
| Model | Price |
|---|---|
GPT-Live-1 (openai_live) | $0.05/min, billed per second |
GPT-Live hands reasoning and tool calls to a backend model (delegation.model, gpt-5.6-luna). That model's tokens are billed on top of the per-minute rate, at OpenAI's token prices for that model. See OpenAI GPT-Live.
Mistral
Prices per 1M tokens.
| Model | Input | Output |
|---|---|---|
| Mistral Large | $0.50 | $1.50 |
| Mistral Medium | $0.40 | $2.00 |
| Mistral Small | $0.10 | $0.30 |
| Ministral 8B | $0.15 | $0.15 |
| Ministral 3B | $0.10 | $0.10 |
| Codestral | $0.30 | $0.90 |
| Mixtral 8x7B | $0.70 | $0.70 |
| Mixtral 8x22B | $2.00 | $6.00 |
Recommended for voice assistants: Mistral Small (fast + cheap), Mistral Medium (balanced)
Google Gemini (Vertex AI, EU)
Prices per 1M tokens. Gemini as a text model in the STT -> LLM -> TTS pipeline, served through Vertex AI on the platform's service account (llm_config.provider: google, no key to enter). The platform picks the Google location per model: the 3.5 models run in Google's EU multi-region (eu, EU data residency; Google's list price for the multi-region is 10% above the single region and that is what the table shows), the 2.5 models in europe-west4.
| Model | Location | Input | Output |
|---|---|---|---|
| Gemini 3.5 Flash Lite (default) | eu | $0.33 | $2.75 |
| Gemini 3.5 Flash | eu | $1.65 | $9.90 |
| Gemini 2.5 Flash Lite | europe-west4 | $0.10 | $0.40 |
| Gemini 2.5 Flash | europe-west4 | $0.30 | $2.50 |
Recommended for voice assistants: Gemini 3.5 Flash Lite (EU data residency, best value), Gemini 2.5 Flash Lite (cheapest)
Google Gemini Live (speech-to-speech)
Prices per 1M tokens. Select these with llm_config.provider: google_realtime. Two routes, and they differ in more than the model name: gemini-live-2.5-flash-native-audio runs through Vertex AI in europe-west4 with EU data residency, while the Gemini API models below run on Google's global endpoint, which carries no data residency.
| Model | Route | Audio in | Audio out | Text in | Text out |
|---|---|---|---|---|---|
| Gemini 3.8 Live | Gemini API (global) | $3.00 | $12.00 | $0.75 | $4.50 |
| Gemini 3.8 Live Extended Thinking | Gemini API (global) | $3.00 | $12.00 | $0.75 | $4.50 |
| Gemini 3.1 Flash Live | Gemini API (global) | $3.00 | $12.00 | $0.50 | $2.00 |
| Gemini 2.5 Flash Native Audio | Vertex AI, europe-west4 | $3.00 | $12.00 | $0.50 | $2.00 |
Google's text prices for the 3.8 Live models are an introductory rate that runs to 31 December 2026; from 1 January 2027 they double, to $1.50 in and $9.00 out. Audio is unaffected. Billing follows the price that applied on the day of the call, so nothing changes for calls made before that date.
Note on data residency: Gemini 3.8 Live is served only on the global endpoint. If your organization needs EU data residency, stay on the Vertex AI route.
xAI (Grok)
Prices per 1M tokens.
| Model | Input | Output |
|---|---|---|
| Grok 4.1 Fast | $0.20 | $0.50 |
| Grok 4 Fast | $0.20 | $0.50 |
| Grok Code Fast 1 | $0.20 | $1.50 |
| Grok 4 (0709) | $3.00 | $15.00 |
| Grok 3 Mini | $0.30 | $0.50 |
| Grok 3 | $3.00 | $15.00 |
Realtime API (Speech-to-Speech):
| Model | Price |
|---|---|
| Grok Realtime v1 | $0.05/min ($3.00/hr) |
Recommended: Grok 4.1 Fast (best value), Grok Realtime (for S2S)
Text-to-Speech (TTS)
ElevenLabs
Prices per 1,000 characters. Based on Creator tier ($22/mo).
| Model | Price per 1K chars |
|---|---|
| Flash v2.5 | $0.11 |
| Turbo v2.5 | $0.11 |
| Eleven v4 Turbo | $0.11 |
| Eleven v4 | $0.22 |
| Eleven v3 | $0.22 |
| Multilingual v2 | $0.22 |
| Monolingual v1 | $0.22 |
Tier pricing breakdown:
| Tier | Flash, Turbo and v4 Turbo per 1K | Multilingual, v3 and v4 per 1K |
|---|---|---|
| Free | N/A | $0.17 |
| Starter ($5) | $0.08 | $0.17 |
| Creator ($22) | $0.11 | $0.22 |
| Pro ($99) | $0.10 | $0.20 |
| Scale ($330) | $0.08 | $0.17 |
| Business ($1,320) | $0.06 | $0.12 |
Recommended: Flash v2.5 (fastest, cheapest), Multilingual v2 (best quality)
Realtime (speech-to-speech):
| Model | Price |
|---|---|
Eleven Realtime v1 Mini (elevenlabs_realtime) | $0.08/min plus model tokens |
Eleven Realtime v1 Max (elevenlabs_realtime) | $0.08/min plus model tokens, at a higher token rate |
ElevenLabs reports the cost of every conversation, minutes and tokens together, and that reported amount is what is billed. See ElevenLabs Realtime.
Inworld
Prices per 1,000,000 characters (On-demand tier).
| Model | Price per 1M chars | Per 1K chars |
|---|---|---|
| TTS 1.5 Mini | $5.00 | $0.005 |
| TTS 1.5 Max | $10.00 | $0.01 |
| TTS 1 | $5.00 | $0.005 |
| TTS 1 Max | $10.00 | $0.01 |
Note: Inworld is ~20x cheaper than ElevenLabs! At 650 chars/min:
- Inworld 1.5-Mini: $0.00325/min
- Inworld 1.5-Max: $0.0065/min
- ElevenLabs Flash: $0.0715/min
Google Chirp 3 HD (EU)
Prices per 1,000,000 characters. Google Cloud Text-to-Speech with the Chirp 3 HD voices, served from Google's EU location (eu) on the platform's service account. Select it with tts_config.provider: google and model: chirp-3-hd; there is no key to enter. The thirty voices are the same names as Gemini TTS; the full voice name is built from language and voice_id (nl-NL-Chirp3-HD-Kore).
| Model | Price per 1M chars | Per 1K chars |
|---|---|---|
Chirp 3 HD (chirp-3-hd) | $30.00 | $0.03 |
At 650 chars/min that is about $0.0195/min.
VoiceDock (beta)
Prices per 1,000,000 characters. VoiceDock's own voice, running on our own GPU servers in the EU. Select it with tts_config.provider: voicedock; there is no key to enter.
| Model | Price per 1M chars | Per 1K chars |
|---|---|---|
VoiceDock (voicedock-1) | $15.00 | $0.015 |
At 650 chars/min that is about $0.0098/min.
How These Costs Map to Your Bill
The tables above are the raw provider rates. How they reach your HMS Sovereign bill depends on the mode you run an assistant in. By default an assistant runs on HMS Sovereign's platform keys — every provider listed here works out of the box, with no API keys of your own required.
| Mode | What you pay |
|---|---|
| Platform keys (default) | Model usage at cost + €0,07/min orchestration |
| Bring Your Own Key (optional) | Your provider's usage (billed by them) + €0,07/min orchestration |
1 credit = €0,07 (one minute of orchestration).
On platform keys, the model usage from the tables above is passed through at cost and the only HMS Sovereign markup is the €0,07/min orchestration fee. Choosing a lighter STT/LLM/TTS combination lowers the at-cost model portion of your bill; the orchestration fee stays the same. With Bring Your Own Key (optional), your provider bills you directly for that usage instead and HMS Sovereign charges only the €0,07/min orchestration fee.
ElevenLabs Eleven v4
Use ElevenLabs Eleven v4 and Eleven v4 Turbo as the voice of a pipeline assistant: more expressive speech, audio tags and more than 90 languages.
VoiceDock, Flireo & HMS Sovereign
How our company (Flireo B.V.), our product (VoiceDock), and our orchestration technology (HMS Sovereign) relate.