LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K2.7 Code

moonshotai·moonshotai/kimi-k2.7-code·GA·Open weights·kimi-k2 series
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Specs & pricing

Input / output per 1M tokens
Official price·Moonshot AI
$0.95 / $4.00
Blended $1.71 · Cache read $0.19
Lowest paid·routing.runGateway
$0.28 / $1.10
Blended $0.48 · 7.1× spread
Context
262,144
Output limit
262,144
Knowledge cutoff
2025-01
Released / updated
2026-06-12 / 2026-06-12
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Weights
Hugging Face

Kimi K2.7 Code by moonshotai is offered by 69 providers on this page. Public prices are shown for 65 of them. Its official list price is $0.95 per 1M input tokens and $4.00 per 1M output tokens. The lowest paid channel is routing.run at $0.275 / $1.10 per 1M, about 3.6× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 4 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 56 tokens per second, with 2.88s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 200,000 to 271,360, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed56 tok/s
TTFT2.88 s

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

Available at 69 providers65 with public prices · 4 subscription-covered

  • ProviderInput / Output
  • SCNet Token PlanGateway
    Kimi-K2.7-Code
    Subscription
    Cache read $0Context 262,144Output limit 262,144
  • Alibaba Token PlanGateway
    Subscription
    Cache read $0Context 262,144Output limit 262,144
  • Alibaba Token Plan (China)Gateway
    Subscription
    Cache read $0Context 262,144Output limit 262,144
  • Volcengine Ark Coding PlanGateway
    Subscription
    Cache read $0Context 262,144Output limit 262,144deprecated
  • routing.runGateway
    $0.28 / $1.10
    Context 200,000 ⚠Output limit 32,000
  • routing.runGateway
    kimi-k2.7-code-nitro
    $0.28 / $1.10
    Context 200,000 ⚠Output limit 32,000
  • KenariGateway
    kimi-k2-7-code
    $0.57 / $2.86
    Cache read $0.11Context 262,144Output limit 262,144
  • CoreWeaveCloud
    moonshotai/Kimi-K2.7-Code
    $0.60 / $3.00
    Cache read $0.12Context 262,144Output limit 262,144
  • NanoGPTGateway
    $0.60 / $3.00
    Cache read $0.12Context 262,144Output limit 65,536
  • OpenRouterGateway
    $0.60 / $3.00
    Cache read $0.12Context 262,144Output limit 235,929
  • Moonshot AIOfficialFirst-party
    $0.95 / $4.00
    Cache read $0.19Context 262,144Output limit 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
SCNet Token Plan
Kimi-K2.7-Code
GatewaySubscription$0—262,144262,144
Alibaba Token PlanGatewaySubscription$0$0262,144262,144
Alibaba Token Plan (China)GatewaySubscription$0$0262,144262,144
Volcengine Ark Coding PlanGatewaySubscription$0—262,144262,144deprecated
routing.runGateway$0.28$1.10——200,000 ⚠32,000
routing.run
kimi-k2.7-code-nitro
Gateway$0.28$1.10——200,000 ⚠32,000
Kenari
kimi-k2-7-code
Gateway$0.57$2.86$0.11—262,144262,144
CoreWeave
moonshotai/Kimi-K2.7-Code
Cloud$0.60$3.00$0.12—262,144262,144
NanoGPTGateway$0.60$3.00$0.12—262,14465,536
OpenRouterGateway$0.60$3.00$0.12—262,144235,929
Moonshot AIOfficialFirst-party$0.95$4.00$0.19—262,144262,144

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.

Reasoning control

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

Interleaved thinking (reasoning between tool calls) is declared by 40 of 69 providers.

47 / 69 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1routing.run$110.00
2routing.run$110.00
3Kenari$202.29
4CoreWeave$212.40
5NanoGPT$212.40
6OpenRouter$212.40
21Moonshot AI · Official$298.80

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

Switch to routing.run to save $188.80/mo (63%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.00$02026-08-052026-08-13
2026-08-13Input list $0.95Output list $4.00Min blended $0.48

Benchmark6 items

NameConditionsScoreMetricSource
Kimi Code Benchharness: Kimi Code CLI · vv262—Source ↗
Program Benchharness: Kimi Code CLI53.6—Source ↗
MLS Bench Liteharness: Kimi Code CLI35.1—Source ↗
MCP Atlasharness: Kimi Code CLI76success rateSource ↗
MCP Mark Verifiedharness: Kimi Code CLI81.1success rateSource ↗
Kimi Claw 24/7 Benchharness: Kimi Code CLI46.9—Source ↗

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

Artificial Analysis evaluations18 items

GPQA Diamond89.6%
Humanity's Last Exam35.0%
HLE-Diamond14.8%
CritPt10.0%
SciCode47.8%
Terminal-Bench Hard44.7%
Terminal-Bench 2.167.4%
Terminal-Bench 4.01.0%
τ²-Bench Telecom90.1%
τ³-Bench Banking20.2%
AutomationBench-AA24.4%
EnterpriseOps-Gym-AA40.2%
AA-Briefcase858
GDPval-AA1046
GDP.pdf11.2%
AA-LCR79.3%
MLCR-AA12.2%
IFBench63.1%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Kimi K2.8 Previewsame series—Kimi K2.7 Code Highspeedsame series—Kimi K2.6same series$0.95 / $4.00GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20
Data partly from models.dev (MIT) · Moonshot AI official docs ↗