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
pre.dev is a long-horizon coding agent that plans, builds, and verifies software over extended runs in the browser or terminal. It connects to many SaaS tools, publishes previews, and sells separate RL coding tasks to AI labs through pre.dev Labs.
Explore toolWindsurf, renamed Devin Desktop on 2 June 2026, is Cognition's AI code editor with an Agent Command Center for running local and cloud (Devin) coding agents, plus Tab completions and inline edits. Paid plans use shared usage quotas.
Explore toolKiro is an agentic engineering environment from AWS that turns prompts into specs, validates code, and runs parallel agents across large repos. It offers a desktop app, CLI installer, and credit-based paid tiers with access to open-weight and premium models.
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.