LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K3

moonshotai·moonshotai/kimi-k3·BETA·Open weights·kimi-k3 series·NEW
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Kimi K3 by moonshotai is offered by 88 providers on this page. Public prices are shown for 80 of them. Its official list price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is CrofAI at $2.00 / $8.00 per 1M, about 9.0× 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 3 free ($0) channels and 5 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 43.6 on the Intelligence Index, with 76.2 for coding and 50 for agentic tasks. Against its lowest blended price of $3.50 per 1M, that is roughly 12 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 44 tokens per second, with 3.74s to the first token. Running one task of the Artificial Analysis suite costs about $2.0001, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 262,144 to 1,113,088, 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.

Specs & pricing

Input / output per 1M tokens
Official price·Moonshot AI (China)
$3.00 / $15.00
Blended $6.00 · Cache read $0.30
Lowest paid·CrofAIGateway
$2.00 / $8.00
Blended $3.50 · 9× spread
3 more $0 channels
Context
1,048,576
Output limit
1,048,576
Knowledge cutoff
—
Released / updated
2026-07-16 / 2026-07-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF

Quality & performanceArtificial Analysis · Intelligence Index v4.3 · rep. tier Max

Intelligence43.6
Value12
Coding76.2
Agentic50
Output speed44 tok/s
TTFT3.74 s
Cost per task$2.00
Value formulaIQ 43.6 ÷ min blended $3.500 = 12
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
LowIQ 30.1 · 44 tok/s
MaxIQ 43.6 · 44 tok/s

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

Available at 88 providers80 with public prices · 3 free · 5 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
SenseNova (China)GatewayFree$0—1,048,57665,536
Umans AI Coding Plan
umans-kimi-k3
GatewaySubscription$0$01,048,576131,072
Volcengine Ark Coding PlanGatewaySubscription$0—1,048,576131,072
Kimi For Coding (kimi.com)
k3
GatewaySubscription$0$01,048,576131,072
SCNet Token Plan
Kimi-K3
GatewaySubscription$0—1,048,576131,072
NvidiaCloudFree——1,048,576131,072
KenariGatewayFree——1,048,576131,072
Kimi For Coding (kimi.ai)
k3
GatewaySubscription$0$01,048,576131,072
CrofAIGateway$2.00$8.00$0.25—1,000,000 ⚠262,144
engyGateway$1.95$9.75$0.20—1,113,088 ⚠65,536
Moonshot AI (China)OfficialFirst-party$3.00$15.00$0.30—1,048,5761,048,576

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

effort = loweffort = higheffort = maxToggle (on / off)effort = nonebudget_tokens ≥ 1,024effort = mediumeffort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 43 of 88 providers.

7 / 88 providers expose no reasoning control (reasoning_options: []).

Experimental modes1 items

ModeProviderInputOutputCache readCache write
priorityFireworks AI$3.75$18.75$0.38—

Your usage cost

1CrofAI$590.00
2engy$666.90
3NanoGPT$684.00
4ainetcafe$729.00
5OpenRouter$780.00
6Vancine$820.80
16Moonshot AI (China) · Official$1,026.00

8 more channels offer $0 (SenseNova (China), Umans AI Coding Plan, Volcengine Ark Coding Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to CrofAI to save $436.00/mo (42%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$15.00$02026-08-052026-10-022026-08-05 · Input list $3.002026-08-06 · Input list $3.002026-08-07 · Input list $3.002026-08-08 · Input list $3.002026-08-09 · Input list $3.002026-08-10 · Input list $3.002026-08-11 · Input list $3.002026-08-12 · Input list $3.002026-08-13 · Input list $3.002026-09-20 · Input list $3.002026-09-22 · Input list $3.002026-09-25 · Input list $3.002026-09-26 · Input list $3.002026-10-01 · Input list $3.002026-10-02 · Input list $3.002026-08-05 · Output list $15.002026-08-06 · Output list $15.002026-08-07 · Output list $15.002026-08-08 · Output list $15.002026-08-09 · Output list $15.002026-08-10 · Output list $15.002026-08-11 · Output list $15.002026-08-12 · Output list $15.002026-08-13 · Output list $15.002026-09-20 · Output list $15.002026-09-22 · Output list $15.002026-09-25 · Output list $15.002026-09-26 · Output list $15.002026-10-01 · Output list $15.002026-10-02 · Output list $15.002026-08-05 · Min blended $3.502026-08-06 · Min blended $3.502026-08-07 · Min blended $3.502026-08-08 · Min blended $3.502026-08-09 · Min blended $3.002026-08-10 · Min blended $3.002026-08-11 · Min blended $3.002026-08-12 · Min blended $3.002026-08-13 · Min blended $3.502026-09-20 · Min blended $3.402026-09-22 · Min blended $3.502026-09-25 · Min blended $3.302026-09-26 · Min blended $3.502026-10-01 · Min blended $3.022026-10-02 · Min blended $3.50

Benchmark13 items

NameConditionsScoreMetricSource
DeepSWEharness: Kimi Code · variant: max effort · v1.167.5resolve rateSource ↗
Terminal-Benchharness: Kimi Code · variant: max effort · v2.188.3accuracySource ↗
FrontierSWEharness: Kimi Code · variant: max effort81.2dominance scoreSource ↗
Program Benchharness: Kimi Code · variant: max effort77.8scoreSource ↗
SWE Marathonharness: Claude Code · variant: max effort · v1.142resolve rateSource ↗
GDPval-AAvariant: max effort · vv21668EloSource ↗
AA-Briefcasevariant: max effort1548EloSource ↗
AutomationBenchvariant: max effort · dataset: 600-task public subset30.8success rateSource ↗
JobBenchvariant: max effort52.9scoreSource ↗
SpreadsheetBenchharness: Claude Code · variant: max effort · v234.8scoreSource ↗
BrowseCompvariant: max effort, context compaction91.2accuracySource ↗
CharXiv Reasoningvariant: max effort, with tools91.3accuracySource ↗
ZeroBenchvariant: max effort, with tools41pass@5Source ↗

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

Artificial Analysis evaluations6 items

GPQA Diamond93.5%
Humanity's Last Exam46.9%
SciCode59.5%
Terminal-Bench 2.185.0%
τ³-Bench Banking46.0%
AA-LCR88.7%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Kimi Fast Latestsame series$4.50 / $22.50Kimi K3 Fastsame series$4.50 / $22.50Kimi K3-256Ksame series$0 / $0GLM-5.2cheaper alternative$1.40 / $4.40GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flashcheaper alternative$0.15 / $0.60
Data partly from models.dev (MIT) · Moonshot AI (China) official docs ↗