Kimi K3.1 Pro vs Kimi K3 Low: benchmark scores compared

Kimi K3.1 Pro leads the intelligence index 46.5 to 17.4. Kimi K3.1 Pro costs 33% less on blended price. Benchmarks, sample bills, speed and a verdict.

Metric	Kimi K3.1 Pro	Kimi K3 (Low)
Intelligence Index	46.5	17.4
Input price (per 1M tokens)	$2.00	$3.00
Output price (per 1M tokens)	$10.00	$15.00
Output speed (tokens/s)	27	49
Time to first token	3.0s	3.6s
Release date	2026-10-23	2026-07-16

Metric

Kimi K3.1 Pro

Kimi K3 (Low)

Intelligence Index

46.5

17.4

Input price (per 1M tokens)

$2.00

$3.00

Output price (per 1M tokens)

$10.00

$15.00

Output speed (tokens/s)

Time to first token

3.0s

3.6s

Release date

2026-10-23

2026-07-16

Staying with Kimi still leaves a decision: Kimi K3.1 Pro or Kimi K3 (Low). No hands-on testing went into this write-up; it summarises the recorded benchmark, price and speed data for both models. The headline gap is on the intelligence index, where Kimi K3.1 Pro scores 46.5 and Kimi K3 Low 17.4.

Kimi K3.1 Pro leads on the intelligence index

Kimi K3.1 Pro comes out ahead on the intelligence index, 46.5 to 17.4. A gap this large suggests the two are built for different jobs.

For context, that places Kimi K3.1 Pro 23rd and Kimi K3 Low 86th out of 109 scored models still on offer.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Which is newer

Kimi K3 Low came first, on July 16, 2026; Kimi K3.1 Pro followed on October 23, 2026.

Kimi K3 Low is the faster writer

Once a response is under way, Kimi K3.1 Pro produces roughly 27 tokens per second against 49 tokens per second for Kimi K3 Low. Kimi K3 Low is ahead by 83% on throughput. The wait for the first token averages 3.0 seconds on Kimi K3.1 Pro against 3.6 seconds on Kimi K3 Low. Short replies favour Kimi K3.1 Pro; beyond about 50 tokens, Kimi K3 Low claws the time back.

Add the two numbers up for a 2,000-token reply and Kimi K3 Low finishes first: 77 seconds for Kimi K3.1 Pro, 44 seconds for Kimi K3 Low.

Cost: Kimi K3.1 Pro is cheaper

Per million tokens, Kimi K3.1 Pro charges $2.00 for input and $10.00 for output, while Kimi K3 Low charges $3.00 and $15.00. Kimi K3 Low costs 1.5 times as much per output token.

For a sample workload of 1 million input tokens and 200,000 output tokens, Kimi K3.1 Pro would cost $4.00 and Kimi K3 Low $6.00, a difference of $2.00. A bigger example, extracting fields from 20,000 pages of 1,500 tokens into 150-token records, costs $90.00 on Kimi K3.1 Pro and $135 on Kimi K3 Low: a gap of $45.00.

Value for money

A blunt value measure, blended price over intelligence score, puts Kimi K3.1 Pro at $0.086 and Kimi K3 Low at $0.34 per point. Kimi K3.1 Pro scores higher and costs less per point, so on price per point there is nothing to trade off.

FAQ

Is Kimi K3 Low better than Kimi K3.1 Pro?

Not across the board: Kimi K3.1 Pro scores higher on the intelligence index, 46.5 to 17.4; Kimi K3.1 Pro is 33% cheaper on blended price; Kimi K3 Low streams output 1.8 times as fast; and Kimi K3.1 Pro reaches its first token sooner.

Who makes Kimi K3.1 Pro and Kimi K3 Low?

Both are Kimi models, listed as separate models in the catalogue. Kimi K3.1 Pro was released on October 23, 2026 and Kimi K3 Low on July 16, 2026.

How much do Kimi K3.1 Pro and Kimi K3 Low cost?

Kimi K3.1 Pro is cheaper on a blended basis. Kimi K3.1 Pro lists $2.00 per million input tokens and $10.00 per million output tokens; Kimi K3 Low lists $3.00 and $15.00. For 1 million input and 200,000 output tokens that is $4.00 against $6.00.

Was this comparison tested by hand?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Which model has lower latency?

Kimi K3 Low generates output faster, at 49 tokens per second against 27 tokens per second. Kimi K3.1 Pro reaches its first token sooner (3.0 seconds against 3.6 seconds). Counting the first-token wait, Kimi K3.1 Pro finishes short replies first and Kimi K3 Low pulls ahead beyond about 50 tokens.

Final whistle

In one line: Kimi K3.1 Pro has more going for it here, but Kimi K3 Low is not without an argument. Pick Kimi K3.1 Pro if you need the higher overall score (46.5 against 17.4) and cost matters ($10.00 against $15.00 per million output tokens). Pick Kimi K3 Low if your outputs often run past about 50 tokens.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the Kimi K3.1 Pro and Kimi K3 (Low) pages. The AI Benchmark methodology explains how that data is collected and shown.