Minaco

Kimi K3.1 Pro

Kimi K3.1 Pro is the newer Kimi flagship, following K3. Moonshot’s current Kimi Code documentation highlights coding and long-horizon agent work.

When to try it.

Try a cross-module change that benefits from understanding a large body of project context, with a staged plan and verifiable outputs.

What to weigh

Minaco publishes this exact model identity. Kimi’s membership-specific high-speed variants are separate; do not assume they are included.

A first task

Map this feature’s dependencies and propose a refactor that preserves behavior. Verify each stage before moving on.

This is a suggested evaluation task. Check the result against your own requirements; it is not a benchmark or a guarantee of performance.

Know the rate.

Currently published for Kimi Code. Rates below are Minaco Credits per one million tokens.

Input
4,000
Cached input
400
Output
20,000

Cache writes: 4,000 Credits per million tokens.

Estimate a model call

Example: 10,000 uncached input tokens and 1,000 output tokens cost approximately 60 Credits before per-request rounding.

An agent turn may make several model calls. Context, tool results and billable reasoning tokens affect the total; enter cache-write tokens separately when applicable. The prompt total determines the rate for the whole request. This estimate is not a charge cap or a checkout quote. How Credits work.

Exact route: moonshotai/kimi-k3.1-pro

Catalog checked 2026-11-17. Model access depends on your plan and current service availability.

Use it in your workspace.

  1. Prepare Kimi Code

    Install Minaco on your Apple silicon Mac, connect your account and prepare the native agent in Agent settings.

  2. Choose the exact model

    Select Kimi Code and a Minaco-credit account mode. If your plan offers Kimi K3.1 Pro, choose it from the model selector. Desktop 0.13.14 or later reads the server’s model catalog.

  3. Give it a bounded task

    Open the project folder, provide the necessary context and review any approvals. Inspect the result and usage before expanding the scope.

When the next stage calls for a different agent, finish the turn and switch in the same conversation. Minaco prepares the visible working context for the next native session; hidden reasoning and credentials do not transfer.

How context handoff works →

Read the source.

Kimi model documentation describes the upstream model.

Editorial review: 2026-11-11. Task suggestions and comparisons are Minaco’s guidance, not vendor benchmark results. Minaco is an independent workspace; model API features do not imply that every feature is exposed by the native agent.

Compare nearby choices.

  • Kimi K3 — Kimi K3 remains available alongside K3.1 Pro. Kimi’s documentation describes it for codebase analysis, multi-file refactoring and long-document work.

Keep the work moving.

Your agents. Your workspace. One place to continue.

Download for Mac