Kimi K2.7 Code is the current Kimi coding-model search page. Moonshot’s Kimi API docs position it as the strongest Kimi coding model, with kimi-k2.7-code and kimi-k2.7-code-highspeed IDs, 256K-class context, multimodal input, thinking required, automatic context caching, ToolCalls, JSON Mode, and Partial Mode.
Use K2.7 Code when you want Kimi’s current coding release. Keep K2.6 in the comparison set because it is still a relevant multimodal/API lane and exact-match search term, not because it is the newest Kimi coding release.
Quick Facts
| Spec | Kimi K2.7 Code |
|---|---|
| Provider | Moonshot AI / Kimi |
| Model IDs | kimi-k2.7-code, kimi-k2.7-code-highspeed |
| Context window | 262,144 tokens, commonly described as 256K |
| Thinking | Required for K2.7 Code; disabling thinking throws an error |
| Base API pricing | $0.19 cache-hit input / $0.95 cache-miss input / $4.00 output per 1M tokens |
| HighSpeed pricing | $0.38 cache-hit input / $1.90 cache-miss input / $8.00 output per 1M tokens |
| Useful for | Coding agents, multimodal coding tasks, Kimi-native API workflows |
| Caveat | Vendor benchmark claims and speed claims need workload-level checks |
K2.7 Code vs K2.6
| Question | K2.7 Code | K2.6 |
|---|---|---|
| Current coding release | Yes | Prior current release and still relevant comparison lane |
| Model IDs | kimi-k2.7-code, kimi-k2.7-code-highspeed | kimi-k2.6 |
| Context | 256K-class | 256K-class |
| Thinking mode | Required | Can be enabled or disabled |
| Cache-hit input | $0.19 / 1M | $0.16 / 1M |
| Cache-miss input | $0.95 / 1M | $0.95 / 1M |
| Output | $4.00 / 1M | $4.00 / 1M |
| Fast variant | HighSpeed at $0.38 / $1.90 / $8.00 | No separate HighSpeed price page in the current docs |
The short version: choose K2.7 Code for current coding-model tests and K2.6 when you need non-thinking mode, have existing integrations, or are comparing exact K2.6 pricing/search intent.
Kimi Code And API Routing
Kimi’s official coding surfaces have moved beyond the old “Kimi k2.5 only” framing. Current Kimi docs describe Kimi Code and API paths around newer Kimi flagship models, with kimi-for-coding acting as a stable tool-facing model ID in some official coding-tool contexts and K2.7 Code available through the API.
That means older Kimi k2.5 guides still matter for historical/free-access intent, but current coding-model searches should land here or on the Kimi access guide:
- Access Kimi for membership, promo-check, and access routing.
- Kimi Code for the official coding membership and tool path.
- Kimi K2.5 for older K2.5 context and legacy free-access paths.
GLM-5.2 vs Kimi K2.7 Code
| Decision point | Kimi K2.7 Code | GLM-5.2 |
|---|---|---|
| Context | 256K-class | 1M |
| Base input pricing | $0.19 cache hit / $0.95 cache miss | $1.40 input / $0.26 cached input |
| Output pricing | $4.00 | $4.40 |
| Speed lane | HighSpeed at 2x token price | GLM Coding Plan or API path |
| Tool fit | Kimi API, Kimi Code, Claude Code-compatible Kimi paths, OpenAI-compatible API | Z.AI-supported coding tools and OpenAI/Anthropic-compatible endpoints |
| Best first test | Kimi-native coding, multimodal tool calls, cheaper cache-hit workloads | Whole-repo context and long-horizon refactors |
For the full decision table, use GLM-5.2 vs Kimi K2.6/K2.7.
Eval Plan
Before switching your daily coding lane:
| Test | What to check | Pass signal |
|---|---|---|
| Coding bug | One real failing test | Correct small patch, no broad churn |
| Long context | Medium repo or feature area | Maintains constraints through follow-up turns |
| Tool calls | Multi-step agent task with tool results | Preserves reasoning/tool context and recovers from failures |
| Multimodal | Screenshot, UI clip, or video task | Uses visual input concretely rather than guessing |
| Cost | Cache-hit and cache-miss workload | Total cost per accepted patch beats your fallback |
Related links
- /compare/models/glm-5.2-vs-kimi-k2.6/ - GLM vs Kimi coding-model decision guide
- /models/glm-5.2/ - Z.AI’s current GLM coding model
- /tools/kimi-code/ - Official Kimi coding membership and tool path
- /value/kimi-access/ - Kimi access, membership, and promo-check guidance
- /value/smart-spend/ - Paid-stack routing strategy
- /compare/models/mid-range/ - Production spend-band comparison
Sources
- Kimi K2.7 Code quickstart
- Kimi K2.7 Code pricing
- Kimi model list
- Kimi K2.6 quickstart
- Kimi K2.6 pricing
- Z.AI GLM-5.2 docs
Last verified: June 20, 2026. Kimi model IDs, pricing, membership quotas, and HighSpeed availability can change quickly.