AI Worldwire

· Frontier and open models · 8 min read

Kimi K3.1 Pro Review: Strong Scores, Slow, Weights Due 4 Nov

Moonshot AI's Kimi K3.1 Pro ranks fourth of 221 models on Artificial Analysis's independent index at a mid-range price, but it is slow and its open weights are still a promise. OpenAI's GPT-6.1 Terra arrived three days later at half the per-token price; Artificial Analysis scores it 48.

Key takeaways

What Moonshot released

Kimi K3.1 Pro is a post-trained version of K3, which VentureBeat says was released in July, with much more post-training compute, according to Moonshot [1][7]. Moonshot calls it a "3T-class" model, which VentureBeat reads as roughly three trillion parameters [7]. It has a one-million-token context window and always thinks: reasoning effort can be set to low, high or max, and defaults to max [2][3].

It is live on kimi.ai, the Kimi apps (iOS, Android, HarmonyOS), Kimi Work, Kimi Code and the Kimi API [1]. Enterprise administrators must switch it on, because access is off by default [1]. API use requires a minimum $1 top-up [3].

How it scores: independent versus vendor numbers

Artificial Analysis, an independent evaluator, gives K3.1 Pro an Intelligence Index of 55 [4]. Its leaderboard puts it above GPT-6 Astra and Gemini 4 Argon (53 each) and GPT-6.1 Sol (52), and behind Claude Opus 5.5 (58), Claude Sonnet 5.5 (56) and Meta's Muse Wonder Full (56), each at its best-scoring setting [6][14]. Artificial Analysis currently lists it as proprietary with no open weights [4].

Moonshot's own tests are more flattering. It reports 65.7% on Terminal-Bench 4.0 with the Claude Code harness, ahead of GPT-6 Astra (58.2%) and just behind Claude Opus 5.5 (66.4%) [1]. On BenchCAD with tools it reports 92.7%, behind Opus 5.5 (96.2%) [1]. Moonshot says it took rival scores from their own reports or public leaderboards and notes that proprietary model testing may involve fallback behaviour, so these are not controlled head-to-head runs [1].

Strengths and weaknesses

Strengths. It takes text and image input and has a one-million-token window at flat per-token prices, with cached input at $0.20 per million [2][4]. Moonshot says it excels at long-running coding, 3D and CAD work and financial workflows, which are company claims [1].

Weaknesses. Artificial Analysis measures 41.4 output tokens per second against a median of 88, and calls it noticeably slow [4]. It used 150 million output tokens to run the index, against a median of 81 million, so it is verbose [4]. Moonshot's own hallucination test, which it describes as a stress test and not a real-world error rate, puts the claim-level rate at 8.3% with tools, down from 23.4% for K3 [1].

Pricing and availability

Model Input per million tokens Output per million tokens Cached input Source
Kimi K3.1 Pro $2.00 $10.00 $0.20 Moonshot price list [2]
Kimi K3.1 Pro Highspeed $4.00 $20.00 $0.20 Moonshot price list [2]
Kimi K3 $3.00 $15.00 $0.30 Moonshot price list [2]
GPT-6.1 Terra $1.00 $5.00 $0.05 OpenAI announcement [8]

Moonshot says Highspeed is two to three times faster with identical capability [1]. Regional restrictions are not stated on Moonshot's pages. VentureBeat reports that the US Department of Homeland Security order covering DeepSeek does not name Kimi [7].

Open questions: weights, promotion and provenance

The weights and licence are the main gap. Moonshot says it removed cyber-related data from training and that its own test shows the result is weaker at exploit tasks than an unmodified checkpoint (81.0% against 90.5%), a company claim [1].

A promotion dispute is unresolved. An X user posted screenshots he said were instructions for a Kimi creator campaign that asked posts to omit the paid-partnership label; VentureBeat says the document is not authenticated and no Moonshot response had surfaced by 25 October [7][9].

Earlier allegations also remain contested. White House science adviser Michael Kratsios said on 22 July that the US had information Moonshot distilled Anthropic's Fable for K3, without publishing evidence, and Moonshot's business head denied it [10][11]. Anthropic's September threat report attributes more than 23 million exchanges between May and July 2026 to Moonshot; these are Anthropic's claims, not independently audited [12]. None of this changes the independent scores.

The global picture

On 26 October OpenAI announced GPT-6.1 Terra at $1 and $5 per million tokens, with ChatGPT access for Plus, Pro, Enterprise and Edu users and the API name gpt-6.1-terra [8][13]. OpenAI's benchmark claims are its own; Artificial Analysis has since scored Terra 48 at maximum reasoning effort, seven points below K3.1 Pro [6]. DeepSeek's V4.1-Flash is cheaper still; see our 20 October review. For another Chinese-versus-US price comparison, see our Meta Muse Wonder review.

Regions not covered today: Europe, India, Japan and Korea, the Gulf, Russia and Australia.

Best fit, and who should wait

K3.1 Pro suits long-document analysis, agentic coding and finance work where the index score and context window matter more than latency. Teams wanting to self-host should wait for the weights and licence. Anyone building real-time chat, or needing independent reruns of the vendor numbers, should wait too.

What to watch next

Our take

Our analysis: the independent score and the price are the news; the vendor charts are marketing until reproduced. A 55 on Artificial Analysis would be notable for open weights, but "open" is a promise until 4 November. OpenAI answering with a $1/$5 model within days shows price is now the main competitive lever.

FAQ

Are the Kimi K3.1 Pro weights available? Not yet. Moonshot says full weights will be released by 4 November 2026 and its announcement names no licence [1].

Is Kimi K3.1 Pro better than Claude Opus 5.5? Not on the Artificial Analysis index, where it scores 55 against 58 for Opus 5.5 [6][14]. Moonshot's own charts show it close on some tests and behind on others [1].

How much does it cost? $2 per million input tokens and $10 per million output tokens on Moonshot's API [2].

Sources

  1. Introducing Kimi K3.1 Pro, Moonshot AI, 23 October 2026. Primary.
  2. Model inference pricing, Kimi API Platform, read 27 October 2026. Primary.
  3. Kimi K3.1 Pro quickstart, Kimi API Platform, read 27 October 2026. Primary.
  4. Kimi K3.1 Pro: intelligence, performance and price, Artificial Analysis, read 27 October 2026. Independent evaluator; primary for its own measurements.
  5. Moonshot AI releases Kimi K3.1 Pro, Unite.AI, 24 October 2026.
  6. LLM leaderboard, Artificial Analysis, read 27 October 2026. Independent evaluator; primary for its own measurements.
  7. Moonshot's Kimi K3.1 Pro flirts with open weights leadership amid paid influencer scandal allegations, VentureBeat, 24 October 2026.
  8. Introducing GPT-6.1 Terra, OpenAI, 26 October 2026. Primary.
  9. Moonshot Kimi K3.1 Pro tops benchmarks amid influencer allegations, AI Weekly, 25 October 2026.
  10. Senior White House official accuses Moonshot AI of copying Anthropic's leading frontier model, SiliconANGLE, 23 July 2026.
  11. Moonshot denies distilling Fable and credits K3 gains to its own architecture, Implicator, 23 July 2026.
  12. Detecting and countering misuse of AI: September 2026, Anthropic, September 2026. Primary (Anthropic's allegations).
  13. OpenAI launches GPT-6.1 Terra with API pricing 50% lower than GPT-5.6 Terra, gHacks, 27 October 2026.
  14. Kimi K3.1 Pro launches at 4th on the Intelligence Index, Artificial Analysis, October 2026. Independent evaluator; primary for its own measurements.

AI Worldwire is independent and has no commercial relationship with the companies covered, unless stated. Research and drafting are assisted by AI; every article is reviewed and approved by a human editor before publication. Subscribe to the AI Worldwire newsletter. Last updated: 27 October 2026.

Disclosure: the AI system that assisted this article, Claude, is made by Anthropic, one of the companies covered here.

Subscribe to the AI Worldwire newsletter