Kimi K3.1 Pro: specs, benchmarks, pricing & API options
Kimi K3.1 Pro is Moonshot AI’s new flagship, released on October 23, 2026, and the headline is a number we have not been able to write about an open-weights model before: Artificial Analysis measures it at 55 on its Intelligence Index (v4.3.2) — #4 of every model it tracks, 3 points off the index leader (Claude Opus 5.5, 58), one point behind Claude Sonnet 5.5 at the same $2 / $10 list price, and 9 points above the best open-weights model on the index today (MiMo-V2.6-Pro, 46).
The “open-weights” part is a promise, not a download yet: Moonshot says the full weights ship by November 4, 2026. Until then K3.1 Pro is API-only. It is a post-trained Kimi K3 — same 2.8T-parameter MoE, same 1M-token context, “substantially larger post-training compute” in Moonshot’s words — released alongside a K3.1 Pro Highspeed variant with the same capabilities at 2–3× the output speed.
And to answer the question this blog exists to answer: yes, we are going to serve it. K3.1 Pro is confirmed for the Flagship Pool, where Kimi K3 is served unlimited today. It goes live when the weights are published, the license permits commercial serving and we have validated capacity for a model of this size — the live status is always on the models-under-review page.
Kimi K3.1 Pro specs
Section titled “Kimi K3.1 Pro specs”| Architecture | Mixture-of-Experts, ~2.8T total parameters (“3T-class” in Moonshot’s wording) — a post-trained Kimi K3, not a new base model |
| Context window | 1M tokens (1,048,576); no long-context price surcharge |
| Input | Text, image and video; text output |
| Reasoning | Reasoning model — thinking is always on. reasoning_effort accepts low, high and max (default max); Moonshot’s docs state that requests with thinking disabled are rejected with HTTP 400 |
| Variants | kimi-k3.1-pro · kimi-k3.1-pro-highspeed (same capabilities, 2–3× the output speed, 2× the price) |
| Open weights | Announced for November 4, 2026; license not yet published. Cyber-related data was removed from the open-weight training stages |
| List price (API) | $2.00 in / $10.00 out per 1M, cached input $0.20 — Highspeed $4.00 / $20.00. Kimi K3 was $3.00 / $15.00 |
| Measured speed | 52.2 output tok/s, 2.97s to first token on Moonshot’s API (Artificial Analysis) |
Two things are new relative to K3 beyond the scores. The price went down a third for a better model ($2/$10 vs $3/$15 — the first time a Kimi flagship has been cheaper than its predecessor), and the reasoning configuration got stricter: K3 let you turn thinking off for fast direct answers; K3.1 Pro does not.
The vendor benchmarks, charted
Section titled “The vendor benchmarks, charted”Moonshot’s own reported numbers (vendor harness — not independently reproduced), against the two closed models it chose to compare with. The third row is a hallucination rate, so lower is better there:
| Benchmark (Moonshot, vendor-run) | Kimi K3 | Kimi K3.1 Pro | Claude Opus 5.5 | GPT-6 Astra |
|---|---|---|---|---|
| Terminal-Bench 4.0 | — | 65.7 | 66.4 | 58.2 |
| Kimi Code Bench 3.0 (long-horizon, internal) | 55.95 | 61.2 | — | — |
| BenchCAD, with tools | — | 92.7 | 96.2 | 95.9 |
| BenchCAD, without tools | — | 72.8 | 73.0 | — |
| OfficeQA Pro v2 | — | 64.4 (claimed state of the art) | — | — |
| Kimi Hallu Bench Hard, with tools (claim-level hallucination rate, lower = better) | 23.4% | 8.3% | 15.0% | 5.5% |
| Internal finance evals: Financial Modeling · Financial Research · Business Operation | 50.4 · 58.8 · 8.9 | 57.6 · 70.4 · 37.0 | — | — |
Read the pattern rather than any single cell. On the agentic benchmarks Moonshot leads with, K3.1 Pro lands within a point of Claude Opus 5.5 (Terminal-Bench 4.0, BenchCAD without tools) and clearly ahead of GPT-6 Astra on terminal work; on tool-augmented CAD it trails both closed models by 3–4 points. Against its own predecessor the jumps are large everywhere Moonshot measured them — and the hallucination number is the one to hold loosely: it is Moonshot’s own adversarial stress test (the company itself says it does not reflect everyday error rates), but a drop from 23.4% to 8.3% on the same test is a real change in behaviour. Terminal-Bench scores also move by tens of points with scaffolding, so the 7.5-point gap to GPT-6 Astra is a direction, not a measurement.
Where it lands on the Intelligence Index
Section titled “Where it lands on the Intelligence Index”The independent signal, from Artificial Analysis on Intelligence Index v4.3.2 — every score below re-checked today on that edition (AA rescored the whole field in September, so none of these numbers compare with scores quoted from earlier editions):
| Model | AA Intelligence Index v4.3.2 | List price in / out per 1M | Weights |
|---|---|---|---|
| Claude Opus 5.5 (max) | 58 | $4 / $20 | closed |
| Claude Sonnet 5.5 (max) | 56 | $2 / $10 | closed |
| Kimi K3.1 Pro | 55 | $2 / $10 | announced for Nov 4 |
| GPT-6 Astra (max) · Claude Fable 5.1 (max) | 53 | $10 / $50 | closed |
| MiMo-V2.6-Pro | 46 | $0.43 / $0.87 | open (MIT) |
| GLM-5.3 (max) · Qwen3.8 Max | 45 | $1.40 / $4.40 · $2 / $6 | open |
| Kimi K3 (max) | 44 | $3 / $15 | open |
Scores from the current index edition; prices are vendor list prices for the variants AA evaluates. Full field and history in our monthly LLM Pareto Frontier report.
The honest read. K3.1 Pro does not beat the closed frontier: Claude Opus 5.5 leads at 58, and Claude Sonnet 5.5 edges it by one point at the identical $2/$10 list price — which is why, on our Pareto chart, K3.1 Pro sits one point under the frontier line rather than on it. What is remarkable is the column on the right. Every model within 3 points of the top of the index is closed except this one, and this one has weights due in nine days. The day they land, the open-vs-closed gap on the index goes from 12 points (MiMo-V2.6-Pro’s 46 against 58) to 3 — and the best open-weights score on record jumps 9 points in a single release, more than the 6-point jump K3 itself delivered in July.
Two more facts from the same AA page keep the enthusiasm calibrated: K3.1 Pro is verbose (150M output tokens to complete the index, against a median of 87M — expect that at $10/M), and it is not fast (52.2 tok/s, in the lower range for its price tier). The Highspeed variant exists for the second problem, at twice the price.
Pricing: Kimi K3.1 Pro API vs Kimi K3
Section titled “Pricing: Kimi K3.1 Pro API vs Kimi K3”| Kimi K3 | Kimi K3.1 Pro | K3.1 Pro Highspeed | |
|---|---|---|---|
| Input, per 1M tokens | $3.00 | $2.00 | $4.00 |
| Cached input, per 1M | $0.30 | $0.20 | $0.20 |
| Output, per 1M tokens | $15.00 | $10.00 | $20.00 |
| AA Intelligence Index | 44 | 55 | — (same model, faster serving) |
At K3’s launch we called it “the first open flagship priced like a closed mid-tier model”. K3.1 Pro keeps that bracket and moves the bar: $10 per million output tokens for an index score that only two closed models beat. The per-token shape is still the one where a flat fee pays off fastest — reasoning always on, verbose by measurement, 1M context — which is exactly the profile the Flagship Pool exists for: Kimi K3 is served there unlimited from $199/mo, and K3.1 Pro is confirmed for the same pool.
The weights: November 4, license to be announced
Section titled “The weights: November 4, license to be announced”Moonshot’s commitment is explicit — full weights by November 4, 2026 — and the K3 precedent is encouraging: K3’s weights shipped on the day promised, under Moonshot’s own Kimi K3 License rather than the K2 line’s Modified MIT. The K3.1 Pro license text has not been published, so until it is, “open weights” is a date, not a fact; our State of Open Weights report adds the row the day the Hugging Face card exists.
One detail worth noting for anyone evaluating models to serve: Moonshot removed cyber-related data from the open-weight training stages, and published the cost — on its xdev-bench-hard cyber benchmark the final K3.1 Pro scores 81.0 (pass@3) where a checkpoint without that removal scored 90.5. That is a deliberate capability trade made before the weights go public, and a first for a frontier-class open release.
Where it stands in our review
Section titled “Where it stands in our review”We are going to serve Kimi K3.1 Pro. It is confirmed for the Flagship Pool, next to the models it supersedes and sits beside — Kimi K3 and Qwen3.8 Max — on the same unlimited time-block subscriptions. Three things gate the launch, in order: the weights publishing (November 4), a license that permits commercial serving, and capacity validation for a 2.8T-parameter model with reasoning always on. Until then nothing changes for Flagship subscribers: K3 keeps being served, existing keys keep working, and the models-under-review page carries the live status. The addition lands in the changelog the day it ships.
Common questions
Section titled “Common questions”What is Kimi K3.1 Pro? Moonshot AI’s flagship model, released October 23, 2026: a post-trained version of Kimi K3 (~2.8T-parameter MoE) with a 1M-token context window, text, image and video input, and reasoning always on. Artificial Analysis scores it 55 on its Intelligence Index (v4.3.2), #4 overall and 3 points off the leader. Full open weights are announced for November 4, 2026.
How much does the Kimi K3.1 Pro API cost? Moonshot lists $2.00 per 1M input tokens, $0.20 for cached input and $10.00 per 1M output tokens — a third below Kimi K3’s $3 / $15, with no surcharge across the 1M context. The faster K3.1 Pro Highspeed variant is $4.00 / $20.00. Artificial Analysis measures $2.11 per Intelligence-Index task.
Is Kimi K3.1 Pro open-weights? Not yet. Moonshot has committed to releasing the full weights by November 4, 2026; the license has not been published. Until the weights and license are out, the model is available only through Moonshot’s API and apps.
How does Kimi K3.1 Pro compare to Kimi K3? Same architecture and context window, much more post-training. On the AA index it scores 55 against K3’s 44 (both on v4.3.2); on Moonshot’s own tests it gains 5 points on Kimi Code Bench long-horizon tasks, cuts the adversarial hallucination rate from 23.4% to 8.3%, and improves 7–12 points on internal finance evals. It is also cheaper per token ($2/$10 vs $3/$15), but thinking can no longer be switched off.
Is Kimi K3.1 Pro better than Claude Sonnet 5.5 or Opus 5.5? On the AA Intelligence Index, no — narrowly. Opus 5.5 scores 58 and Sonnet 5.5 scores 56 to K3.1 Pro’s 55, and Sonnet 5.5 costs the same $2/$10. On Moonshot’s vendor benchmarks K3.1 Pro is within a point of Opus 5.5 on Terminal-Bench 4.0 (65.7 vs 66.4) and BenchCAD without tools (72.8 vs 73.0). The difference the index does not show: K3.1 Pro’s weights are due to be public, which no model above 46 on the index can say.
What is Kimi K3.1 Pro Highspeed? The same model served 2–3× faster, at twice the price ($4 / $20 per 1M). Moonshot’s documentation describes identical capabilities; it exists because the standard model’s measured 52 tok/s is slow for interactive use.
Is there an unlimited Kimi K3.1 Pro API subscription? Not today — K3.1 Pro is confirmed for the Flagship Pool and goes live once the weights are published and validated (live status). Its predecessor Kimi K3 is served there unlimited now, from $199/mo: flat monthly fee, no token caps during your reserved hours, OpenAI- and Anthropic-compatible, and it works in Claude Code.
CheapestInference serves Kimi K3 and Qwen3.8 Max (Flagship Pool), GLM 5.3 and MiniMax M3 (Frontier Pool) and DeepSeek V4.1 Flash and MiMo V2.6 Flash (Core Pool) through one OpenAI- and Anthropic-compatible API on unlimited time-block subscriptions. See the pools or get started.