Overview
Kimi K2.7 Code is Moonshot AI's June 2026 coding-focused successor to Kimi K2.6. It is not a general "Kimi K2.7" replacement for every task: Moonshot positions K2.7 Code specifically for long-horizon coding, software engineering agents, and developer tooling where instruction following, repository-scale context, and tool-use reliability matter more than broad chat versatility.
At its June 12, 2026 launch, K2.7 Code was the Kimi Code default. As of October 24, 2026, the Kimi Code membership model ID kimi-for-coding instead selects K2.8 Preview, while kimi-for-coding-highspeed explicitly selects K2.7 Code Highspeed. The separately billed Kimi Platform API continues to offer the standard model through kimi-k2.7-code, and its open weights remain available on Hugging Face. Moonshot has announced that K2-series API models will stop being offered to newly registered users from October 31, 2026, with retirement of the K2 series planned by the end of December 2026. Existing API users are not affected by the October 31 registration restriction. See the official Kimi API pricing and availability documentation. Compared with K2.6, the biggest practical changes are stronger coding benchmark results, roughly 30% lower thinking-token usage on average, and a clearer split between coding-first workflows and general-purpose use. Moonshot still recommends K2.6 for broad writing, analysis, and conversation tasks.
What's New
Coding-First K2.6 Successor
K2.7 Code keeps the K2.6 base direction but narrows the optimization target to coding and agentic software engineering. Moonshot's official materials describe it as a coding-focused agentic model designed for real-world long-horizon tasks such as feature work across multiple files, codebase refactoring, debugging, and agent sessions that need to carry context over many steps.
That positioning matters for users choosing between models. At its June launch, K2.7 Code was the coding-focused successor to K2.6. This comparison describes that release context; current Kimi Code offers newer K3.1 Pro and K2.8 Preview models.
Lower Thinking-Token Usage
K2.7 Code reduces average thinking-token usage by about 30% compared with K2.6 while improving benchmark scores. For developers this is not just a latency metric: thinking tokens compound across every agent loop, test run, edit cycle, and tool call. Lower reasoning overhead can reduce API cost and make interactive coding sessions feel faster without disabling thinking mode.
There is one important constraint: K2.7 Code does not support non-thinking mode. The API requires thinking to stay enabled, and current Kimi Code documentation routes disabled-thinking requests for the legacy highspeed model to K2.8 Preview instead. API users should treat this as a model behavior contract rather than an optional style setting.
Open Weights and 256K Context
Moonshot released K2.7 Code as an open-source model with weights on Hugging Face. The architecture remains a 1T-parameter Mixture-of-Experts model with 32B activated parameters per token, Multi-head Latent Attention, 384 experts, 8 selected experts per token, and a 262,144-token context window. It also includes the MoonViT vision encoder, so the model card and official page describe text, image, and video input support.
For teams already testing K2.6 locally or through the API, the most relevant continuity points are the 256K-class context window and OpenAI-compatible API surface. The main migration work is model selection and retesting, not a new application architecture.
Kimi Code Default and API Access
K2.7 Code became the Kimi Code default at its June launch; that statement no longer describes the current model selection. Developers can call it through the Kimi Platform API using the documented model ID kimi-k2.7-code; Kimi Code membership integrations use the stable kimi-for-coding model ID, whose backend can change; as of October 24, Kimi Code maps it to K2.8 Preview rather than K2.7 Code. At the June 12, 2026 release, Moonshot announced K2.7 Code HighSpeed as an upcoming beta rather than a generally available feature. Kimi Code officially launched its HighSpeed option on July 9, 2026, and the Kimi Platform API now documents kimi-k2.7-code-highspeed. Moonshot initially stated that HighSpeed capacity was limited and that speed could fluctuate while capacity expanded.
The API documentation calls out stricter parameter behavior than many chat models: temperature is fixed at 1.0, top_p is fixed at 0.95, n must be 1, and frequency/presence penalties are fixed at 0.0. Tool use also has compatibility rules around tool_choice and preserving reasoning_content across multi-step tool calls.
Performance Benchmarks
Moonshot evaluates K2.7 Code against K2.6 across coding and agentic benchmarks. These are official results; several benchmarks are Moonshot internal, so production teams should still run their own workload tests before replacing a stable K2.6 deployment.
| Benchmark | K2.6 | K2.7 Code | Change |
|---|---|---|---|
| Kimi Code Bench v2 | 50.9 | 62.0 | +21.8% |
| Program Bench | 48.3 | 53.6 | +11.0% |
| MLS Bench Lite | 26.7 | 35.1 | +31.5% |
| Kimi Claw 24/7 Bench | 42.9 | 46.9 | +9.3% |
| MCP Atlas | 69.4 | 76.0 | +9.5% |
| MCP Mark Verified | 72.8 | 81.1 | +11.4% |
The standout signal is not a single benchmark win, but the combination of better coding scores and lower thinking-token usage. K2.7 Code is designed to complete more agentic work per budget unit, especially in repeated edit-test-debug loops.
Availability & Access
K2.7 Code is available through three main paths:
| Access Path | Details |
|---|---|
| Kimi Code | Historical June default; current Code maps kimi-for-coding to K2.8 Preview, while the legacy Highspeed ID remains available |
| Kimi API | Use kimi-k2.7-code for the standard model or kimi-k2.7-code-highspeed for the faster variant |
| Hugging Face | Open weights under Moonshot AI's official Kimi-K2.7-Code model page |
For API use, K2.7 Code requires thinking mode and has fixed sampling parameters. For local deployment, the model's 1T total parameter MoE architecture means infrastructure requirements are substantial even though only 32B parameters are activated per token.
Pricing & Plans
Kimi offers K2.7 Code in both subscription-style Kimi Code plans and usage-based API billing.
Kimi Code membership pricing is separate from API billing. The following table records legacy Kimi Code membership plans and their monthly-equivalent prices under annual billing, rather than the current plan names offered to new subscribers. Kimi has introduced new membership tiers, including Plus and Pro. New memberships no longer have weekly usage quotas, while existing legacy memberships retain their original plan names and quota rules. Under the current model configuration, K2.7 Code Highspeed requires Pro or above on new plans, or Allegretto or above on legacy plans. The historical prices below should not be presented as current offers for new subscribers. Verify current pricing and eligibility against the official Kimi Code membership documentation:
| Plan | Monthly Price | Best for |
|---|---|---|
| Moderato | $15/month | Regular coding workflows with weekly refreshed usage quotas |
| Allegretto | $31/month | Larger weekly limits and higher concurrency caps |
| Allegro | $79/month | Intensive development tasks and larger projects |
| Vivace | $159/month | Highest weekly quotas for complex projects and large codebases |
Earlier USD API rates for kimi-k2.7-code are recorded below for historical context. Check the current regional quote before estimating a new workload:
| Unit | Cache-Hit Input | Cache-Miss Input | Output | Context Window |
|---|---|---|---|---|
| 1M tokens | $0.19 | $0.95 | $4.00 | 262,144 tokens |
Prices exclude applicable taxes and can change, so teams should confirm the official Kimi pricing documentation before committing production budgets.
Best For
- Developers using Kimi Code for repository-scale feature work, debugging, and refactoring.
- Teams building AI agent systems where coding tasks require many tool calls and long context.
- API users who want a coding-specialized alternative to K2.6 with lower average thinking-token usage.
- Open-weight model evaluators comparing Moonshot against MiniMax, DeepSeek, Qwen, Claude Code, and Codex-style coding agents.
- Engineering teams that need 256K-class context for large codebases but want stronger coding-specific behavior than a general chat model.
FAQ
Is Kimi K2.7 Code the same as a general Kimi K2.7 model?
No. Moonshot's public positioning is specifically "Kimi K2.7 Code." It is optimized for coding and agentic software engineering. The original release comparison recommended K2.6 for general-purpose work. Current model selection should also consider K3 and K3.1 Pro.
What model ID should API users call?
Use kimi-k2.7-code for the standard API model. Moonshot also documents kimi-k2.7-code-highspeed for faster coding sessions. API users should keep thinking enabled and follow the documented fixed-parameter constraints.
Is Kimi K2.7 Code open-source?
Yes. Moonshot released the model weights on Hugging Face under the official moonshotai/Kimi-K2.7-Code model page. Self-hosting still requires substantial infrastructure because the model is a 1T-parameter MoE with 32B activated parameters per token.
How much context does K2.7 Code support?
K2.7 Code supports a 262,144-token context window, the same 256K-class context size used in K2.6. That makes it suitable for large repositories, long issue threads, and multi-step coding sessions.
Should existing K2.6 users upgrade?
K2.7 Code was the coding-focused upgrade from K2.6 at its June launch. For a new evaluation today, compare the newer K3.1 Pro family as well, rather than assuming the June default is still the latest option.
Current Compatibility Note
This page documents the June K2.7 Code release. As of October 24, Kimi Code identifies kimi-for-coding-highspeed as K2.7 Code Highspeed, while kimi-for-coding selects K2.8 Preview. Select k3.1-pro or k3.1-pro-highspeed explicitly for the new family; see the K3.1 Pro upgrade guide.
Sources
Official Kimi Code release notes: original June 12 release event.
K2.7 Code API guide: release capabilities and API behavior.
Current Kimi Code model configuration: current model aliases and routing.
Current Kimi Code membership: legacy versus new plan rules.
Kimi API pricing and availability: K2-series registration restrictions and planned retirement.
