Moonshot Works from Russia Code and terminal
Kimi Code CLI
An open MIT shell for the terminal, desktop and VS Code; Kimi Code comes with a Kimi membership from Plus up, and Moonshot doesn't restrict access from Russia.
Price and access
- Free?
- The program is free, the model is paid
- Price
- CLI is free; model by Moonshot key or a Kimi plan from ¥99 (Plus)
- From Russia
- A Russian developer paid for Kimi with a Mir card and used it without a VPN (Habr report, 1 November 2026); there is no official country list.
- Models
- Kimi K3.1 Pro · K3
- Licence
- MIT
- Our benchmark
- Kimi K3: 8.95 of 10, rank 2 →
Official pricing page ↗ Checked 3 November 2026.
What changed in price and access
- A Kimi subscription can be paid with a Russian Mir card and used without a VPN, according to a Russian developer's report on Habr ↗
- Kimi K3.1 Pro released as an open model: available in the Kimi apps and the API, full weights promised by 4 November ↗
- Kimi Code 2.4 imports Claude Code and Codex sessions from the last 15 or 30 days, and plans no longer self-approve in auto mode ↗
- Fireworks released Ember-1, a Kimi K3 derivative that matches its quality with 40% fewer tokens ↗
- Kimi K3 arrived on Amazon Bedrock – the first open-weights model there with explicit prompt caching ↗
Changes for this tool in total: 7. The full feed for all agents →
What it gives a manager
- Kimi Business: from two seats, an admin invites and removes people, and company data is not used to train the model
- Tower mode: a task is split into missions on separate branches, and every change gets its own review before it is merged
- kimi rc prints a link and QR code – from a phone you can follow the task, reply to the agent and approve its actions
- Imports Claude Code and Codex sessions from the last 15 or 30 days, so task history survives a team switch
Weak points
- Em Dash cancelled after 6 months: since the K3 launch responses are slow and quota drains fast, and moving from $39 to $99 changed nothing.
- Quota is shared with every Kimi feature: if documents and research use up the month, Kimi Code freezes until the reset.
- No cost or elapsed time shown for a session; spend on the Moonshot platform dashboard lags by about 10 minutes.
- Plans were reworked again: the entry Go tier has no coding, Kimi Code starts at Plus for ¥99, legacy plans keep their own rules.
How to check this agent’s work
- Read the plan before it runs: since version 2.4 it no longer approves itself in auto mode.
- Import a Claude Code or Codex session and compare how two agents solved the same task.
- Check the outcome with a second model from another vendor.
Picking an agent takes an evening. After that the question is not the price but whether you can trust what it did.
You’re on the list
We will write when enrolment opens. Meanwhile, here is what the course covers.
The short course programmeWhat the course covers: programme and price
Strengths
- Terminal, a desktop app for macOS, Windows and Linux, and a VS Code extension, MIT licence; sign in with a Kimi membership, no keys.
- In AI Coding Daily's test the same K3 model cost $0.49 in Kimi Code versus $0.85 in OpenCode with the same result: all tests passed.
- kimi web starts a local browser UI with full session history; in swarm mode four subagents added an avatar upload field in parallel.
- Picks up the same AGENTS.md and .agents skills other agents use with no setup; accepts screen recordings as input and MCP servers.
Alternatives
Kilo Code
ZCode
DeepSeek HarnessWho it is for
- Engineering team in Russia without a security sign-off
- Small team that wants one annual bill for its seats
Example from a review: Hardening a CSV contact importer in Laravel
The reviewer gave the same prompt to Kimi Code and to OpenCode, both on K3: make a Laravel contact CSV importer robust to UTF-8, odd line endings and other edge cases. Both runs passed the hidden evaluation tests with no errors (one memory-dependent test skipped). Kimi Code cost $0.49 against $0.85 through OpenRouter, OpenCode took 8 minutes 19 seconds, and the Kimi Code transcript was about half as long. The video is sponsored by Moonshot; the reviewer states the company had no say over the results.
Source: AI Coding Daily, I Tried Kimi Code with Kimi K3: Deep-Dive Review
Reviews (2)
The video authors’ opinions, not our conclusions.
- I Tried Kimi Code with Kimi K3: Deep-Dive Review · AI Coding Daily, 13 August 2026The reviewer (sponsored by Moonshot) finds K3 a stable model and Kimi Code rough around the edges, but was impressed by kimi web and swarm mode.
- Kimi Code Plan after 4 months of use (Honest Review) · Em Dash, 4 September 2026In the reviewer's view Moonshot builds excellent models but cannot serve them; after six months he cancelled the subscription and moved to another provider.
Facts with sources
- The coder / explore / plan subagents run in isolated contexts. Source (in Russian)
- Access via OAuth or key; the bill depends on how much the agent read and wrote. Source (in Russian)
- Since version 2.0 (17 September) Kimi Code CLI runs on Node.js and ships alongside a desktop app; the old Python client kimi-cli is archived. Source
- K3.1 Pro arrived in Kimi Code on 23 October with up to 1 million tokens of context; full context and the Highspeed version start at the Pro plan. Source
- New China plans: Plus ¥99, Pro ¥199, Max ¥699, Ultra ¥1,399 a month; they have no weekly limit, only a 5-hour window and a monthly quota. Source
- Kimi Business costs ¥4,200 per seat a year, 2 to 150 seats per purchase, billed annually only; Kimi Code is included. Source
