Hyprcore Cloud bills usage in credits. They cover AI work that happens on Hyprcore-managed infrastructure: cloud STT, AI summaries, session chat, and embeddings.Documentation Index
Fetch the complete documentation index at: https://docs.hyprcore.ai/llms.txt
Use this file to discover all available pages before exploring further.
| Plan | Monthly credits |
|---|---|
| Free | 0 |
| Pro | 5,000 |
| Team | 12,500 (shared across team) |
What costs how much
Estimates—exact values vary by model and length:| Action | Approx. credits |
|---|---|
| Transcribe 1 minute of audio (cloud STT) | ~6 |
| Summarize a 30-minute meeting (fast model) | ~15 |
| Summarize a 30-minute meeting (smart model) | ~80 |
| Embed 100 pages of text | ~2 |
| Session chat question (small context) | ~5 |
| Session chat question (large context, multi-meeting) | ~30 |
See your usage
app.hyprcore.ai/dashboard/usage shows:- Credits used this cycle
- Remaining credits
- Breakdown by action (STT, summaries, chat, embeddings)
- For Team plans: usage per member
Stretch your credits
- Use local models for routine work. Local Whisper / Parakeet for STT. Apple Intelligence or Ollama for cleanup. Free.
- Pick smaller LLMs for cleanup. Claude Haiku, GPT-4o-mini, and Gemini Flash are 5–10× cheaper than their big siblings, often without a noticeable quality drop on short transcripts.
- Bring your own keys. Plug in your Anthropic, OpenAI, Deepgram, or Groq keys. Hyprcore charges no markup; you pay the provider’s published price directly.
- Skip cloud STT for short meetings. Local Whisper is fine under 30 minutes.
Run out of credits
When your monthly budget hits zero:- Cloud STT stops; Hyprcore falls back to local models if your provider policy allows.
- AI summaries and chat error out unless you’ve configured a BYO key as a fallback.
- Sync keeps working—it doesn’t use credits.
- Local features keep working—dictation, local transcription, vault, search.
- Wait for the cycle to reset.
- Buy a one-time credit pack from Billing → Buy credits.
- Configure a BYO key in Settings → Models → Post-processing so Hyprcore can route around credit exhaustion.
Bring your own keys
Adding a BYO key removes the credit cost for that provider entirely. Hyprcore makes the API call as you, using your key. Your provider invoices you directly. To add a key, see the relevant model setup page:- Speech models (Deepgram, Groq, OpenAI Whisper)
- Post-processing LLMs (Anthropic, OpenAI, Google, Groq, OpenRouter)