← Model list

Kimi K2.6

moonshotai·moonshotai/kimi-k2.6·BETA·Open weights·kimi-k2 series

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

At a glance
Official price$0.95 / $4.00 per 1M
Cache read $0.16 · Moonshot AI
Lowest paid$0.22 / $1.14
DevPass (LLM Gateway) Gateway · 8.1× spread
5 more $0 channels
Context262,144
⚠ Providers report 65,536–262,144; the table below is authoritative
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Knowledge cutoff2025-01
Released / updated2026-04-21 / 2026-04-21

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence45.1
Value100
Coding61.8
Agentic31.2
Output speed46 tok/s
TTFT2.74 s
Cost per task$0.3653
Value formulaIQ 45.1 ÷ min blended $0.449 = 100
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 35.4 · 40 tok/s
defaultIQ 45.1 · 46 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 65 providers59 with public prices · 2 free · 3 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree262,144262,144deprecated
Alibaba Token PlanGatewaySubscription$0$0262,144262,144
Kenari
kimi-k2-6
GatewayFree262,144262,144
SCNet Token Plan
Kimi-K2.6
GatewaySubscription$0262,144262,144
Alibaba Token Plan (China)GatewaySubscription$0$0262,144262,144
DevPass (LLM Gateway)Gateway$0.22$1.14$0.048262,144262,144
routing.runGateway$0.275$1.10200,00032,000
Vultr
moonshotai/Kimi-K2.6
Cloud$0.30$1.20262,144131,072
CrofAIGateway$0.50$1.99$0.05262,144262,144
NanoGPTGateway$0.50$2.60$0.125256,00065,536
Moonshot AIOfficialFirst-party$0.95$4.00$0.16262,144262,144

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

1DevPass (LLM Gateway)$80.21
2routing.run$110.00
3Vultr$120.00
4CrofAI$145.50
5NanoGPT$185.00
6Neuralwatt$236.90
26Moonshot AI · Official$295.20

5 more channels offer $0 (Nvidia, Alibaba Token Plan, Kenari etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to DevPass (LLM Gateway) to save $214.99/mo (73%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark5 items

NameConditionsScoreMetricSource
SWE-Bench Verified80.2resolvedSource ↗
Artificial Analysis Coding Agent Indexharness: Claude Code50.5average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Claude Code59.8pass@1Source ↗
SWE-Bench Proharness: Claude Code · dataset: hard-aa27.3pass@1Source ↗
Terminal-Benchharness: Claude Code · v2.164.3pass@1Source ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = maxToggle (on / off)budget_tokens

19 / 65 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.00$02026-08-052026-08-132026-08-05 · Input list $0.952026-08-06 · Input list $0.952026-08-07 · Input list $0.952026-08-08 · Input list $0.952026-08-09 · Input list $0.952026-08-10 · Input list $0.952026-08-11 · Input list $0.952026-08-12 · Input list $0.952026-08-13 · Input list $0.952026-08-05 · Output list $4.002026-08-06 · Output list $4.002026-08-07 · Output list $4.002026-08-08 · Output list $4.002026-08-09 · Output list $4.002026-08-10 · Output list $4.002026-08-11 · Output list $4.002026-08-12 · Output list $4.002026-08-13 · Output list $4.002026-08-05 · Min blended $0.4492026-08-06 · Min blended $0.4492026-08-07 · Min blended $0.4492026-08-08 · Min blended $0.4492026-08-09 · Min blended $0.4492026-08-10 · Min blended $0.4492026-08-11 · Min blended $0.4492026-08-12 · Min blended $0.4492026-08-13 · Min blended $0.449