Plans
The free tier is a complete personal AI assistant — unlimited memory, full safety, all runners. Pro unlocks the full autonomous daemon with multi-channel, advanced security, and managed remote access.
Free vs Pro
Both tiers run the same binary on your machine. You bring your own API keys. The difference is what the software unlocks.
| Free | Pro — $9/month | |
|---|---|---|
| Core AI | ||
| AI / Inference ― BYOK | Unlimited | Unlimited |
| Memory ― all types, hybrid retrieval, consolidation | Unlimited | Unlimited |
| Runners ― Agent , Loop , Coder | All 3 | All 3 |
| Scheduler | 3 active schedules | Unlimited |
| Search, plugins | Full | Full |
| Included AI messages | — (BYOK only) | 100/mo + 50 web searches |
| Safety & Security | ||
| LLM Judge (4 risk levels, escalation) | Full | Full |
| Secret & credential leak detection | Coming soon | Coming soon |
| PII redaction | Full (local) | Full (local) |
| Prompt injection scanning | Essential (static rules) | Advanced ― and frequently updated |
| Channels & Delivery | ||
| Desktop app | Always available | Always available |
| External channels (Telegram, WhatsApp, Slack, iMessage, Discord, and more) | 1 active at a time | Unlimited simultaneous |
| Cross-channel memory continuity | Desktop ↔ 1 channel | All channels seamlessly |
| Delivery | Basic (respond on same channel) | Presence-aware, quiet hours, proactive agent, cascade |
| Infrastructure | ||
| Managed remote access | DIY | Zero-config managed remote access |
| Licence | ||
| Commercial use | Personal only | Permitted |
Free — $0 forever
Download Salmex I/O and run it on your own machine. Unlimited memory, full agentic capabilities, the LLM judge, 3 active schedules, search, and plugins. Desktop chat is always available. Pick one external channel — Telegram, WhatsApp, Slack, Discord, iMessage, or any other supported channel. Switch anytime, but only one active at a time. Free for personal, non-commercial use. No time limit. No trial.
Pro — $9/month, billed annually
The full autonomous daemon. Unlimited schedules. Includes 100 AI messages and 50 web searches per month via managed open-source inference — no API keys needed. Unlimited simultaneous channels with cross-channel memory continuity. Managed remote access — one command, zero config, no ngrok or Cloudflare setup. Advanced prompt injection scanning with cloud-updated rules and weekly updates. Presence-aware delivery with quiet hours, proactive agent, digests, and smart routing. Commercial use licence. 30-day money-back guarantee.
Need more messages? Add credit packs — prepaid packs from $5, powered by five managed models at 5-21x lower cost than cloud AI providers.
Credit Packs
Credit packs are prepaid packs for Pro subscribers who need more AI messages beyond the 100 included monthly. When packs are exhausted, you seamlessly fall back to BYOK (bring your own API keys) — you're never cut off.
Credit packs
| Pack | Price | Approx. messages | Cost/message |
|---|---|---|---|
| Starter | $5 | ~500 | ~$0.01 |
| Standard | $10 | ~1,200 | ~$0.008 (save 17%) |
| Power | $25 | ~3,500 | ~$0.007 (save 30%) |
Managed models
Five models powered by open-source inference. No API keys to manage. No rate limits.
| Model | Input $/MTok | Output $/MTok | Best for |
|---|---|---|---|
| Salmex Pro 92% of Sonnet 4.6 on SWE-bench | $0.60 | $1.20 | Everyday balanced |
| Salmex Fast 82% of Sonnet 4.6 quality index | $0.20 | $0.80 | Quick answers |
| Salmex Reason Matches o3 on AIME 2025 | $1.50 | $5.00 | Hard problems |
| Salmex Code 89% of Sonnet 4.6 on SWE-bench | $1.00 | $3.00 | Code editing |
| Salmex Think 94% of Sonnet 4.6 on Arena | $0.30 | $1.50 | Long documents |
Our pricing vs. cloud AI
Salmex I/O's managed inference is 5-21x cheaper than calling cloud AI providers directly.
| Provider | Input $/MTok | Output $/MTok | vs Salmex Pro |
|---|---|---|---|
| Claude Sonnet 4.6 | $3.00 | $15.00 | 5-12x more expensive |
| Claude Opus 4.6 | $5.00 | $25.00 | 8-21x more expensive |
| GPT-4o | $2.50 | $10.00 | 4-9x more expensive |
| GPT-5.4 | $2.50 | $15.00 | 4-13x more expensive |
| ChatGPT Plus subscription | $20/mo flat (~$0.025/message) | ~8x more per message | |
All managed models are open-source (DeepSeek, Llama, Qwen). You can always switch to your own API keys for proprietary models like Claude or GPT-4o — BYOK works on every tier.
Frequently asked questions
Is the free tier really free forever?
Yes. No trial, no credit card, no time limit. The free tier includes unlimited memory, full agentic capabilities, the safety judge, 3 active schedules, search, plugins, and desktop chat plus one external channel. Free forever for personal, non-commercial use.
What happens when I run out of included messages?
Pro includes 100 AI messages and 50 web searches per month. If you need more, buy a credit pack (from $5). When packs are exhausted, you fall back to BYOK — bring your own API keys — which is always unlimited. You are never cut off.
Can I use my own API keys with Pro?
Absolutely. BYOK (bring your own key) works on every tier, including Pro. Credit packs are an optional convenience — you can always use your own OpenAI, Anthropic, Gemini, or Ollama keys with zero limits.
How do managed models compare to cloud AI?
Our managed models (powered by open-source inference) are 5-21x cheaper than calling Claude or GPT-4o directly. You also avoid managing API keys, rate limits, and billing across multiple providers. The trade-off: managed models are open-source (DeepSeek, Llama, Qwen) rather than proprietary. You can always switch to your own keys for proprietary models.
What is the refund policy?
Pro comes with a 30-day money-back guarantee. If you're not satisfied, email us within 30 days for a full refund — no questions asked. Credit packs are non-refundable once used.
Will there be a trial period?
We're working on it. In the meantime, the free tier includes every feature except multi-channel, managed access, and commercial use — so you can evaluate the full AI agent before upgrading.