LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K2.5

moonshotai·moonshotai/kimi-k2.5·Deprecated·Open weights·kimi-k2 series
Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Kimi K2.5 by moonshotai is offered by 52 providers on this page. Public prices are shown for 44 of them. Its reference price is $0.56 per 1M input tokens and $3.50 per 1M output tokens. The lowest paid channel is NanoGPT at $0.30 / $1.90 per 1M, about 2.1× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 6 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 36 on the Intelligence Index, with 46.8 for coding and 21.7 for agentic tasks. Against its lowest blended price of $0.70 per 1M, that is roughly 51 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 81 tokens per second, with 2.76s to the first token. Running one task of the Artificial Analysis suite costs about $0.0964, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 256,000 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. 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.

Specs & pricing

Input / output per 1M tokens
Reference price·Venice AI
$0.56 / $3.50
Blended $1.29 · Cache read $0.22
Lowest paid·NanoGPTGateway
$0.30 / $1.90
Blended $0.70 · 2.1× spread
6 more $0 channels
Context
256,000
Output limit
65,536
Knowledge cutoff
2025-01
Released / updated
2026-01 / 2026-01
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning

Intelligence36
Value51
Coding46.8
Agentic21.7
Output speed81 tok/s
TTFT2.76 s
Cost per task$0.0964
Value formulaIQ 36 ÷ min blended $0.700 = 51
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 30.1 · 92 tok/s
ReasoningIQ 36 · 81 tok/s

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

Available at 52 providers44 with public prices · 6 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Alibaba Token PlanGatewaySubscription$0$0262,144 ⚠98,304
Alibaba Coding Plan (China)GatewaySubscription$0$0262,144 ⚠32,768
Alibaba Coding PlanGatewaySubscription$0$0262,144 ⚠32,768
SCNet Token Plan
Kimi-K2.5
GatewaySubscription$0—262,144 ⚠262,144
Tencent Coding Plan (China)GatewaySubscription$0$0262,144 ⚠32,768
Alibaba Token Plan (China)GatewaySubscription$0$0262,144 ⚠98,304
NanoGPTGateway$0.30$1.90$0.15—256,00065,536
DevPass (LLM Gateway)Gateway$0.405$1.98$0.225—262,144 ⚠262,144
LLM GatewayGateway$0.405$1.98$0.225—262,144 ⚠262,144
Deep Infra
moonshotai/Kimi-K2.5
Cloud$0.45$2.25$0.07—262,144 ⚠32,768deprecated

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$137.00
2Deep Infra$156.90
3OpenRouter$156.90
4SiliconFlow$156.90
5Eden AI$156.90
6SiliconFlow (China)$156.90

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

The cheapest paid channel is the only channel.

Benchmark4 items

NameConditionsScoreMetricSource
SWE-Bench Verified—70.8resolvedSource ↗
SWE-Atlas Codebase QnAharness: Mini-SWE-Agent13.1scoreSource ↗
SWE-Atlas Refactoringharness: Mini-SWE-Agent20.95scoreSource ↗
SWE-Atlas Test Writingharness: Mini-SWE-Agent25.77scoreSource ↗

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

Reasoning control

Toggle (on / off)budget_tokens ≥ 1 ≤ 262,144effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max

13 / 52 providers expose no reasoning control (reasoning_options: []).

Related models

Kimi K2.7 Codesame series$0.95 / $4.00Kimi K2.7 Code Highspeedsame series$1.90 / $8.00Kimi K2.7 Code (Free)same series$0 / $0DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Procheaper alternative$0.435 / $0.87GLM-5.3-Flashcheaper alternative$0.075 / $0.25DeepSeek V4 Flash 0731cheaper alternative$0.445 / $1.34

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.50$02026-08-052026-09-072026-08-05 · Input list $0.602026-08-06 · Input list $0.602026-08-07 · Input list $0.602026-08-08 · Input list $0.602026-08-09 · Input list $0.602026-08-10 · Input list $0.602026-08-11 · Input list $0.602026-08-12 · Input list $0.602026-08-13 · Input list $0.602026-08-23 · Input list $0.602026-09-07 · Input list $0.562026-08-05 · Output list $3.002026-08-06 · Output list $3.002026-08-07 · Output list $3.002026-08-08 · Output list $3.002026-08-09 · Output list $3.002026-08-10 · Output list $3.002026-08-11 · Output list $3.002026-08-12 · Output list $3.002026-08-13 · Output list $3.002026-08-23 · Output list $3.002026-09-07 · Output list $3.502026-08-05 · Min blended $0.6882026-08-06 · Min blended $0.6882026-08-07 · Min blended $0.6882026-08-08 · Min blended $0.6882026-08-09 · Min blended $0.6882026-08-10 · Min blended $0.6882026-08-11 · Min blended $0.6882026-08-12 · Min blended $0.6882026-08-13 · Min blended $0.6882026-08-23 · Min blended $0.702026-09-07 · Min blended $0.70
Data partly from models.dev (MIT) · Venice AI official docs ↗