Pricing
Not listed
Official monthly price not confirmed
- API
- Open-source uzu engine and CLI tooling are linked from the homepage with GitHub distribution.
Code · Vendor site 2026-10-04
Mirai Labs builds on-device AI for Apple Silicon through the uzu Rust inference engine, model conversion tooling, and quantized Qwen, LFM, and Muse-Glimmer models. The site emphasizes ultra-low-latency local inference rather than cloud-hosted chat subscriptions.
Developers shipping ambient, low-latency AI experiences on iPhone, iPad, and Mac hardware.
No public monthly SaaS pricing; offerings focus on open-source runtime, models, and services engagements.
Mirai Labs combines uzu, model conversion, and quantized weights to make continuous on-device AI interactions feasible.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| uzu engine | Homepage centers on uzu as a Rust LLM runtime for Apple Silicon devices. | Facts sourced | 2026-10-04 |
| Models | Marketing lists 4-bit/8-bit Qwen, LFM, and Muse-Glimmer models benchmarked against MLX and llama.cpp. | Facts sourced | 2026-10-04 |
| Vision | Copy argues future assistants require ~1,000 tokens per second on-device execution. | Facts sourced | 2026-10-04 |
Understand the total cost
Pricing
Not listed
Official monthly price not confirmed
Degoo is a consumer cloud backup service offering encrypted storage plans from a free tier through paid Pro and Ultimate subscriptions. The marketing site highlights zero-knowledge encryption, multi-device access, referral bonuses, and long-term retention on higher tiers.
Explore toolAppetize.io streams Android emulators and iOS simulators in the browser for demos, support, testing, and Playwright-based mobile automation. Teams launch cloud devices without maintaining local device labs.
Explore toolThe site emphasizes rapid full-stack workflows, built-in CI/CD, preview environments, and pay-as-you-go tiers for solo developers through enterprise self-hosting.
Explore toolThe practical questions
Mirai Labs builds on-device AI for Apple Silicon through the uzu Rust inference engine, model conversion tooling, and quantized Qwen, LFM, and Muse-Glimmer models. The site emphasizes ultra-low-latency local inference rather than cloud-hosted chat subscriptions.
Not confirmed. This record does not confirm an ongoing free plan.
A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.
Open-source uzu engine and CLI tooling are linked from the homepage with GitHub distribution.. API access and subscription access may have different terms; consult the linked sources.
No public monthly SaaS pricing; offerings focus on open-source runtime, models, and services engagements.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.