The everyday workhorse, built for tool use and day-to-day coding. Built on Kimi K2.7 Code, hosted in the US.
Pro moves to Moonshot Kimi K2.7 Code, built for tool use and everyday coding. Reported only on benchmarks Moonshot published (MCP Mark, Kimi Code Bench v2, third-party HumanEval+); no SWE-bench Pro score exists yet, so we do not claim one.
Pro tracks the best open-weight model for tool-driven, day-to-day coding. The version number bumps; the CLI does not change.
Dropstone Pro is the default for the bulk of real engineering: planning, multi-file edits, running tests, and tool-driven workflows where Heavy's budget is unnecessary. It runs Moonshot's Kimi K2.7 Code, a model built for tool use, with strong vendor and third-party scores (MCP Mark 81.1%, Kimi Code Bench v2 62%, third-party HumanEval+ around 94.2%). Moonshot did not publish a SWE-bench Pro number, so we do not place Pro on that chart; putting a tier on a benchmark it has no score for is exactly the mistake our 1.6 evaluation discipline corrects. Same approval-gated CLI, same US-hosted inference.
Plan a feature, edit across the repo, run the test suite, fix the failures. One approval gate per tool call.
Kimi K2.7 Code is built for tool use (MCP Mark 81.1%). Call tools and APIs, edit, run, and iterate, all behind the approval gate.
Run Pro across a PR diff to flag security, performance, and style issues, with the same OWASP coverage as Dropstone's safety analyzer.
Every Dropstone request is treated as if the model could be adversarial. The CLI requires explicit user approval before any action that writes to disk, runs a shell command, or fetches a URL. No model output is ever auto-executed.
Pro runs on SOC 2-certified, US-based inference providers. Enterprise and commercial data is never stored and never trained on, regardless of any setting. Consumer sessions help improve the open model we run and can be turned off anytime in settings, as text only, never your raw images.
Pro is built on Kimi K2.7 Code, an open-weight foundation model. Goldwasser et al. (2022) proved no party can prove a closed foundation model is free of embedded behaviors, including Anthropic for Claude and OpenAI for GPT. We say this out loud. The runtime is why model origin does not matter for your code.
Same approval gate, same US-hosted inference, same zero-retention guarantee across all three. Pick the smallest model that meets the task.
Low-latency agentic coding for edits, refactors, and high-throughput inline completion. Built on DeepSeek V4 Flash, hosted in the US.
The everyday workhorse, built for tool use and day-to-day coding. Built on Kimi K2.7 Code, hosted in the US.
The strongest open-weight model we measured: #1 open on SWE-bench Pro, ahead of GPT-5.5. Built on GLM-5.2, hosted in the US.
Fast is included on every plan. Pro and Heavy are unlocked on the Pro plan ($15/mo) and Max plan ($75/mo).
Install the CLI, authenticate, and start running approval-gated agentic workflows. No credit card to start.
