LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K2 Thinking

moonshotai·moonshotai/kimi-k2-thinking·GA·Open weights·kimi-thinking series
Thinking Kimi model for slower research passes, planning, and hard technical questions

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·HeliconeGateway
$0.48 / $2.00
Blended $0.86 · 1.6× spread
Context
262,144
Output limit
98,304
Knowledge cutoff
2024-08
Released / updated
2025-11-06 / 2025-11-06
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Weights
Hugging Face

Kimi K2 Thinking by moonshotai is offered by 17 providers on this page. Public prices are shown for 16 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Helicone at $0.48 / $2.00 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 1.6× across the providers that host it.

Median output speed is 137 tokens per second, with 1.45s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 32,768 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2024-08.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed137 tok/s
TTFT1.45 s

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

Available at 17 providers16 with public prices

  • ProviderInput / Output
  • HeliconeGateway
    $0.48 / $2.00
    Context 256,000 ⚠Output limit 256,000
  • OpenCodeGateway
    $0.40 / $2.50
    Cache read $0.40Context 262,144Output limit 262,144deprecated
  • Alibaba (China)First-party
    $0.57 / $2.29
    Context 262,144Output limit 16,384deprecated
  • 302.AIGateway
    $0.58 / $2.30
    Context 262,144Output limit 262,144
  • QiniuGateway
    $0.58 / $2.32
    Context 256,000 ⚠Output limit 100,000deprecated
  • NanoGPTGateway
    $0.60 / $2.50
    Cache read $0.15Context 262,144Output limit 98,304
  • Amazon BedrockCloud
    moonshot.kimi-k2-thinking
    $0.60 / $2.50
    Context 262,144Output limit 16,000deprecated
  • Novita AIGateway
    $0.60 / $2.50
    Cache read $0.15Context 262,144Output limit 98,304
  • OpenRouterGateway
    $0.60 / $2.50
    Cache read $0.15Context 262,144Output limit 98,304
  • Eden AIGateway
    amazon/moonshot.kimi-k2-thinking
    $0.60 / $2.50
    Context 256,000 ⚠Output limit 256,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
HeliconeGateway$0.48$2.00——256,000 ⚠256,000
OpenCodeGateway$0.40$2.50$0.40—262,144262,144deprecated
Alibaba (China)First-party$0.57$2.29——262,14416,384deprecated
302.AIGateway$0.58$2.30——262,144262,144
QiniuGateway$0.58$2.32——256,000 ⚠100,000deprecated
NanoGPTGateway$0.60$2.50$0.15—262,14498,304
Amazon Bedrock
moonshot.kimi-k2-thinking
Cloud$0.60$2.50——262,14416,000deprecated
Novita AIGateway$0.60$2.50$0.15—262,14498,304
OpenRouterGateway$0.60$2.50$0.15—262,14498,304
Eden AI
amazon/moonshot.kimi-k2-thinking
Gateway$0.60$2.50——256,000 ⚠256,000

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

budget_tokenseffort = highToggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 8 of 17 providers.

14 / 17 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Vertex$180.20
2NanoGPT$191.00
3Novita AI$191.00
4OpenRouter$191.00
5Kilo Gateway$191.00
6Hugging Face$191.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-10-08
2026-10-08Input list —Output list —Min blended $0.86

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified—71.3resolvedSource ↗

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

Related models

Kimi K2 Instructsame lab—Kimi K2.5same lab—
Data partly from models.dev (MIT)