Models · Moonshot AI (Kimi) · Out sinceReleased 12 Jun 2026

Kimi K2.7 Code

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableCan run on your own serversOpen weights

Kimi K2.7 Code is made by Moonshot AI (Kimi). We don't have enough test results yet to rank it. It's mid-priced to use. Its makers have published it, so you can run it on your own servers.

Coding specialist built on Kimi K2.6 (1T/32B active, modified-MIT). Thinking always on (no instant mode); ~30% fewer thinking tokens than K2.6. 'kimi-k2.7-code-highspeed' variant at $1.90/$8.00. No standalone blog found; HF card is primary source.

Writing & creativity: —
Research & analysis: —
Coding: —
Price: Mid-priced$0.95 / $4
Price per 1M (blended)Blended / 1M: $1.71
MemoryContext: 262K
Longest answerMax output: —
Test resultsResults: 6 (1 independent1 indep.)
Out sinceReleased: 12 Jun 2026
Made byVendor: Moonshot AI (Kimi)
UnderstandsInputs: text, image, video

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

Default

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as moonshotai/kimi-k2.7-code.

Route it as moonshotai/kimi-k2.7-code at $0.67 in / $3.35 out per 1M tokens, 262K context. Listed since 12 Jun 2026.

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Run it yourself

Self-hosting

On your own servers,Licence, sizeunder your own control.and hardware.

Compare all open models →All open-weights models →

Details comingselfHost data pending

This model can be downloaded and run on your own servers. We're collecting its licence, size and hardware needs now.Open-weights model; licence, parameter count, hardware tier and base-model availability will appear after the next data run.

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
						NotesNotes
Kimi Code Bench v2 (internal)	62.0%	Defaultthinking	Maker's own figureVendor-reportedMoonshot AI ↗	12 Jun 2026	Kimi Code CLI	In-house benchmark; temperature 1.0, top_p 0.95, 262,144 ctx
MCP Atlas	76.0%	Defaultthinking	Maker's own figureVendor-reportedMoonshot AI ↗	12 Jun 2026	Kimi Code CLI	100 tool-call budget, avg of 3 runs; temperature 1.0, top_p 0.95, 262,144 ctx
MCPMark Verified	81.1%	Defaultthinking	Maker's own figureVendor-reportedMoonshot AI ↗	12 Jun 2026	Kimi Code CLI	avg of 3 runs; temperature 1.0, top_p 0.95, 262,144 ctx
MLS-Bench-Lite	35.1%	Defaultthinking	Maker's own figureVendor-reportedMoonshot AI ↗	12 Jun 2026	Kimi Code CLI	temperature 1.0, top_p 0.95, 262,144 ctx
ProgramBench (fully resolved)	53.6%	Defaultthinking	Maker's own figureVendor-reportedMoonshot AI ↗	12 Jun 2026	Kimi Code CLI	temperature 1.0, top_p 0.95, 262,144 ctx
SkillsBench	50.0%	Default	Independent testIndependentVals.ai ↗	27 Sep 2026	OpenHands	±4.237 stderr; $0.443/test