← Model list

Kimi K2.7 Code Highspeed

moonshotai·moonshotai/kimi-k2.7-code-highspeed·GA·Open weights·kimi-k2 series·NEW

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

At a glance
Official price$1.90 / $8.00 per 1M
Cache read $0.38 · Moonshot AI
Lowest paid$1.90 / $8.00
AIHubMix Gateway · 1× spread
Context262,144
⚠ Providers report 256,000–262,144; the table below is authoritative
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImageVideoPDF
Knowledge cutoff2025-01
Released / updated2026-06-12 / 2026-06-12

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 10 providers10 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AIHubMixGateway$1.90$8.00$0.322262,14432,768
NanoGPTGateway$1.90$8.00$0.32262,14465,536
Moonshot AIOfficialFirst-party$1.90$8.00$0.38262,144262,144
Merge GatewayGateway$1.90$8.00$0.38262,14432,768
GMI CloudCloud$1.90$8.00$0.38262,144262,144
OfoxGateway$1.90$8.00$0.38262,144262,144
EmpirioLabs AI
kimi-k2-7-code-highspeed
Gateway$1.90$8.00$1.90256,000131,072
Vercel AI GatewayCloud$1.90$8.00$0.38262,14432,768
DevPass (LLM Gateway)Gateway$1.90$8.00$0.38262,144262,144
Moonshot AI (China)OfficialFirst-party$1.90$8.00$0.38262,144262,144

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1NanoGPT$590.40
2AIHubMix$590.55
3Moonshot AI · Official$597.60
4Merge Gateway$597.60
5GMI Cloud$597.60
6Ofox$597.60
Switch to NanoGPT to save $7.20/mo (1%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)budget_tokens ≥ 1 ≤ 32,768effort = loweffort = mediumeffort = higheffort = xhigheffort = max

7 / 10 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$8.00$02026-08-052026-08-132026-08-05 · Input list $1.902026-08-06 · Input list $1.902026-08-07 · Input list $1.902026-08-08 · Input list $1.902026-08-09 · Input list $1.902026-08-10 · Input list $1.902026-08-11 · Input list $1.902026-08-12 · Input list $1.902026-08-13 · Input list $1.902026-08-05 · Output list $8.002026-08-06 · Output list $8.002026-08-07 · Output list $8.002026-08-08 · Output list $8.002026-08-09 · Output list $8.002026-08-10 · Output list $8.002026-08-11 · Output list $8.002026-08-12 · Output list $8.002026-08-13 · Output list $8.002026-08-05 · Min blended $3.422026-08-06 · Min blended $3.422026-08-07 · Min blended $3.422026-08-08 · Min blended $3.422026-08-09 · Min blended $3.422026-08-10 · Min blended $3.422026-08-11 · Min blended $3.422026-08-12 · Min blended $3.422026-08-13 · Min blended $3.42