Deepgram vs Groq: voice AI pricing compared
Updated 2026-11-10 · listed A to Z, not ranked
Deepgram sells speech APIs billed by usage: speech-to-text per minute of audio (billed per second), text-to-speech per 1,000 characters, and its Voice Agent per minute of connection time. A prepaid annual Growth plan lowers the rates.
Groq runs its own LPU inference hardware and sells model access through GroqCloud, an OpenAI-compatible API billed per token (language models), per hour of audio (Whisper) or per character (text to speech).
Listed A to Z, from deepgram.com and console.groq.com. Every figure below is quoted from those pages.
- Main price table
- Flux STT English, Flux STT Multilingual, Nova-3 Monolingual, Nova-3 Multilingual
- Free option
- None in the published plan table
- Published prices
- Speech-to-text from $0.0077 per minute, Aura text-to-speech per 1,000 characters, Voice Agent per minute, and Growth plan rates.
- Main price table
- GPT OSS 120B (openai/gpt-oss-120b), GPT OSS 20B (openai/gpt-oss-20b), Llama 3.1 8B Instant, Llama 3.3 70B Versatile, Whisper Large V3, Whisper Large V3 Turbo
- Free option
- None in the published plan table
- Published prices
- GPT OSS 120B $0.15 in / $0.60 out per 1M tokens, GPT OSS 20B $0.075 / $0.30, Whisper Large V3 Turbo $0.04 per hour.
How we checked: Prices quoted from each official pricing page: Deepgram checked Nov 10, 2026, Groq checked Nov 10, 2026. Taxes, usage overages and promotions can change what you pay; confirm with each provider before you buy.
How they compare
- Main price table. Deepgram lists 4 entries (Flux STT English, Flux STT Multilingual, Nova-3 Monolingual, Nova-3 Multilingual); Groq lists 6 (GPT OSS 120B (openai/gpt-oss-120b), GPT OSS 20B (openai/gpt-oss-20b), Llama 3.1 8B Instant, Llama 3.3 70B Versatile, Whisper Large V3, Whisper Large V3 Turbo).
- Free option. Deepgram: none in the published plan table. Groq: none in the published plan table.
- How prices are quoted. Deepgram: “Speech-to-text”. Groq: “Production models”.
Deepgram plans and prices
| Model | Pay as you go | Growth |
|---|---|---|
| Flux STT English | $0.0077 / min | $0.0065 / min |
| Flux STT Multilingual | $0.0078 / min | $0.0068 / min |
| Nova-3 Monolingual | $0.0077 / min | $0.0065 / min |
| Nova-3 Multilingual | $0.0092 / min | $0.0078 / min |
Add-ons are billed on top, for example speaker diarization $0.0020 / min and redaction $0.0020 / min pay as you go; smart formatting is included.
| Product | Pay as you go | Growth |
|---|---|---|
| Aura-2 TTS | $0.030 / 1k characters | $0.027 / 1k characters |
| Aura-1 TTS | $0.0150 / 1k characters | $0.0135 / 1k characters |
| Flux TTS | $0.0450 / 1k characters | $0.0450 / 1k characters |
| Voice Agent, Standard | $0.075 / min | $0.068 / min |
| Voice Agent, Custom with your own LLM and TTS | $0.050 / min | $0.041 / min |
| Voice Agent, Advanced | $0.163 / min | $0.146 / min |
Voice Agent is one rate covering speech-to-text, a managed language model and text-to-speech; bringing your own LLM or TTS lowers it.
From deepgram.com, checked Nov 10, 2026. Full breakdown: Deepgram pricing.
Groq plans and prices
| Model | Speed (tokens/sec) | Price | Context window |
|---|---|---|---|
| GPT OSS 120B (openai/gpt-oss-120b) | ~500 | $0.15 input / $0.60 output per 1M tokens | 131,072 |
| GPT OSS 20B (openai/gpt-oss-20b) | ~1,000 | $0.075 input / $0.30 output per 1M tokens | 131,072 |
| Llama 3.1 8B Instant | ~560 | Enterprise: contact sales | 131,072 |
| Llama 3.3 70B Versatile | ~280 | Enterprise: contact sales | 131,072 |
| Whisper Large V3 | — | $0.111 per hour of audio | — |
| Whisper Large V3 Turbo | — | $0.04 per hour of audio | — |
Developer plan rate limits on the same page: GPT OSS 120B 250K tokens/min and 1K requests/min; Whisper Large V3 Turbo 400K audio seconds/hour.
| Model | Price |
|---|---|
| Qwen3.8 27B | $0.80 input / $4.00 output per 1M tokens |
| Safety GPT OSS 20B | $0.075 input / $0.30 output per 1M tokens |
| Canopy Labs Orpheus V1 English (TTS) | $22.00 per 1M characters |
| Canopy Labs Orpheus Arabic Saudi (TTS) | $40.00 per 1M characters |
| Llama Prompt Guard 2 22M / 86M | $0.03 / $0.04 per 1M tokens (input and output) |
Groq says preview models may be discontinued at short notice and should not be used in production.
From console.groq.com, checked Nov 10, 2026. Full breakdown: Groq pricing.
FAQ
How much does Deepgram cost?
Speech-to-text from $0.0077 per minute, Aura text-to-speech per 1,000 characters, Voice Agent per minute, and Growth plan rates. (checked Nov 10, 2026).
How much does Groq cost?
GPT OSS 120B $0.15 in / $0.60 out per 1M tokens, GPT OSS 20B $0.075 / $0.30, Whisper Large V3 Turbo $0.04 per hour. (checked Nov 10, 2026).
Do Deepgram and Groq have a free option?
Deepgram: none in the published plan table. Groq: none in the published plan table.
Which is better, Deepgram or Groq?
We do not pick a winner. The two price and package their products differently; the tables above quote each official pricing page so you can match a plan to your own usage.
Where do these prices come from?
Each vendor's own pricing page: deepgram.com (checked Nov 10, 2026) and console.groq.com (checked Nov 10, 2026). Prices change; confirm on the vendor's page before you buy.
Sources (official pages, read 2026-11-10)
Spot something out of date? Email hello@youraitools.co and we’ll fix it.