Models / Kimi K2 Thinking

Moonshot AI

Kimi K2 Thinking

Kimi K2 Thinking is strongest at writing; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is DeepSeek-V4-Flash (0423), at $0.15 per million tokens against $1.07.

Results 16 Nov 2026 · 16 results · 3 sources

Test Kimi K2 Thinking on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.60 in · $2.50 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
22.0
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Moonshot AI, based in China
Weights published
Released
6 Nov 2025
262,144 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 90th of 185Claude Opus 5.5 – $1.07 blended, 57th percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 26th of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $1.07 blended, 57th percentilecheapest: DeepSeek-V4-Flash (0423) –
Models from developers based in China 36th of 75MiMo-V2.6-Pro – $1.07 blended, 74th percentilecheapest: Qwen3.5-9B –
Open-weights models 36th of 104MiMo-V2.6-Pro – $1.07 blended, 79th percentilecheapest: Mistral Nemo –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 138th of 159 available · 29th of 31 at its price
BenchmarkKimi K2 ThinkingRank among availableBest available
OpenHands IndexOpenHands Index: average · reported 41.0% 26th of 31 Claude Fable 5 81.0%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 94th of 187 available · 27th of 35 at its price
BenchmarkKimi K2 ThinkingRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 22.0 90th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 23.8% 93rd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 83.8% 79th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 45th of 169 available · 11th of 28 at its price
BenchmarkKimi K2 ThinkingRank among availableBest available
UGI LeaderboardUGI: writing score · reported 59.3 35th of 124 Gemini 3.8 Flash 78.6
  • Arena (formerly LMArena): has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Kimi K2 Thinking at $1.07 blended, Intelligence Index 22.0. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $1.07 blended per million tokens; quantisation where the host states it: BF16. Cheapest first.

HostQuantisationInputOutputBlended
NovitaBF16$0.60$2.50$1.07

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Kimi K2 ThinkingMuse Spark 1.3
most intelligent at $1–3 per million tokens
DeepSeek-V4-Flash (0423)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $1.07 $2.00$0.15$8.00$0.54
Tokens a second – 254–9643
Intelligence Index 22.0 48.124.457.646.3
Spring Prompt overall – 59–82–
Rank among available models, by use case
Product listings – 17th–13th–
Decks from an analysis – 25th–7th–
User surveys – ––4th–
Marketing planning – 25th–9th–
Agents and tool use 138th of 159 13th59th3rd23rd
Professional work – 8th–3rd–
Reasoning and knowledge 94th of 187 11th69th1st13th
Writing 45th of 169 7th63rd5th23rd
Sticking to the facts – 11th81st3rd10th
Speed under pressure – 33rd–––

Shaded figures are better than Kimi K2 Thinking's. A dash means no result.

Where it has been measured

26th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the bottom quarter for agents and tool use.

Artificial Analysis lists it but has not published a speed for it yet

Every result

16 published results from 3 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 22.0 189 of 413 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 83.8% 142 of 360 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 23.8% 184 of 419 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 68.1% 74 of 288 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 72.0% 182 of 407 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 31.1% 103 of 282 Kimi K2 Thinking 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 93.0% 41 of 286 Kimi K2 Thinking 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 41.0% 28 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 32.4% 19 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 12.5% 25 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 43.6% 26 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 69.2% 26 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 47.3% 27 of 34 Kimi K2 Thinking (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 20.0% 187 of 379 Kimi K2 Thinking 7 Nov 2025
UGI: style adherencescore from 0 to 1, higher is better 0.38 52 of 379 Kimi K2 Thinking 7 Nov 2025
UGI: writing scorescore out of 100, higher is better 59.3 109 of 379 Kimi K2 Thinking 7 Nov 2025

Not shown: Not other format limits such as character counts or bullet counts.

Will Kimi K2 Thinking work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.