Kimi K3.1 Provs.Kimi K3
What has improved?
Kimi K3.1 Pro is clearly ahead in the overall index. Kimi K3.1 Pro costs 67% of the old price per token.
80
Kimi K3.1 Pro
Rank 10 to 13
59
Kimi K3
Rank 18 to 24
36
Kimi K3.1 Pro
slow
55
Kimi K3
slow
$4
Kimi K3.1 Pro
fairly expensive
$6
Kimi K3
expensive
Kimi K3.1 Pro
- Subscription
At Moonshot AI from ≈ €20.14 a month (Kimi Plus, with limited credits). 4 plans in Germany.
- Via API
$2 input, $10 output per 1M tokens.
Kimi K3
- Subscription
At Moonshot AI from ≈ €20.14 a month (Kimi Plus, with limited credits). Through other providers from ≈ €1.06 a month (Command Code Go, with limited credits). 45 plans in Germany.
- Via API
$3 input, $15 output per 1M tokens, unchanged since our price tracking began on Aug 14, 2026.
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
Kimi K3.1 Pro ahead: 6Kimi K3 ahead: 0level: 3too little data: 1of 10 areas
AreaKimi K3.1 ProKimi K30 to 100, higher is betterResult
Areas in the overall index
CodingKimi K3.1 Pro aheadKimi K3.1 Pro: 85Kimi K3: 48
ReasoningKimi K3.1 Pro aheadKimi K3.1 Pro: 80Kimi K3: 53
MathematicsKimi K3.1 Pro aheadKimi K3.1 Pro: 81Kimi K3: 55
KnowledgeKimi K3.1 Pro aheadKimi K3.1 Pro: 85Kimi K3: 44
AgentsKimi K3.1 Pro aheadKimi K3.1 Pro: 80Kimi K3: 49
GenerallevelKimi K3.1 Pro: 74Kimi K3: 72
MultimodalKimi K3.1 Pro aheadKimi K3.1 Pro: 75Kimi K3: 54
Specialist fields
FinancelevelKimi K3.1 Pro: 62Kimi K3: 63
LegallevelKimi K3.1 Pro: 68Kimi K3: 74
Healthonly Kimi K3 has a scoreKimi K3.1 Pro: not enough dataKimi K3: 65
Show 3 more areas that do not count toward the overall index
AreaKimi K3.1 ProKimi K30 to 100, higher is betterResult
Cybersecurityonly Kimi K3 has a scoreKimi K3.1 Pro: not enough dataKimi K3: 75
Productivityonly Kimi K3 has a scoreKimi K3.1 Pro: not enough dataKimi K3: 71
Educationonly Kimi K3 has a scoreKimi K3.1 Pro: not enough dataKimi K3: 55
See for yourself: same task, one attempt
The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Kimi K3.1 Pro
Not tested yet
Kimi K3
Reasoning (requested): high
Current attempt
- Run date
- Oct 1, 2026
- API provider
- openrouter
- Requested API model
- moonshotai/kimi-k3
- API model reported in response
- moonshotai/kimi-k3
- Reasoning setting
- high
- Pinned endpoint
- Moonshot AI | moonshotai/kimi-k3-20260715
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 173.4 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (1)
- Sep 7, 2026API request failedReasoning setting: high
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)SVG short test
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | Kimi K3.1 Pro | Kimi K3 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 80 | 59 |
| Rank | Rank 10 to 13 of 95 | Rank 18 to 24 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $2 | $3 |
| Outputwhat the model writes | $10 | $15 |
| Speed | ||
| Tokens per second | 36 | 55 |
| Technical | ||
| Context windowhow much text the model reads at once | 1.05 M tokens≈ 1,570 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | n/a | n/a |
| Released | Oct 23, 2026 | Jul 16, 2026 |
| Availability | Active | Active |
| Open weights | n/a | yes |
- Kimi K3.1 Pro, API price listed by Artificial Analysis: $2 input, $10 output, and $0.20 cached input per 1 million tokens. Kimi's official API publishes CNY rates separately. Source
- Kimi K3.1 Pro, Official API pricing: K3.1 Pro: CNY 13 input, CNY 68 output, CNY 13 cache write, and CNY 1.30 cache hit per million tokens. Source
- Kimi K3.1 Pro, Highspeed API pricing: CNY 26 input, CNY 136 output, CNY 26 cache write, and CNY 1.30 cache hit per million tokens. Source
- Kimi K3.1 Pro, International API pricing in USD: The international Kimi platform lists $2 input, $10 output, $2 cache write and $0.20 cache hit per million tokens. Highspeed costs $4/$20/$4/$0.20. Checked October 29, 2026. Separately documented CNY tariffs remain separate observations. Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
A: Kimi K3.1 ProB: Kimi K3
HLAB-Vals-1.1Overall · Task fully resolved · higher is betterKimi K3.1 Pro: 11.7%Kimi K3: 12.9%Vals AIAs of 10/26/2026
Legal Research BenchOverall · All-pass · higher is betterKimi K3.1 Pro: 37.5%Kimi K3: 46.2%Vals AIAs of 10/26/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 91%Kimi K3: 87%Vals AIAs of 10/24/2026
Terminal-Bench 4.0Overall · higher is betterKimi K3.1 Pro: 63.6%Kimi K3: 17.2%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceOverall · higher is betterKimi K3.1 Pro: 31.4%Kimi K3: 1.4%Vals AIAs of 10/25/2026
Show 54 more benchmarks
Vibe Code Bench v1.1Overall · higher is betterKimi K3.1 Pro: 84.9%Kimi K3: 85%Vals AIAs of 10/26/2026
Finance Agent v2.1Adjustments · higher is betterKimi K3.1 Pro: 57.4%Kimi K3: 61.8%Vals AIAs of 10/26/2026
HLAB-Vals-1.1Antitrust Competition · Criteria passed · higher is betterKimi K3.1 Pro: 90.4%Kimi K3: 93.1%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterKimi K3.1 Pro: 56.1%Kimi K3: 63.6%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterKimi K3.1 Pro: 10%Kimi K3: 13.3%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterKimi K3.1 Pro: 40%Kimi K3: 13.3%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceEarth Sciences · higher is betterKimi K3.1 Pro: 12.5%Kimi K3: 12.5%Vals AIAs of 10/25/2026
Vals Finance IndexEMB v1.1 · higher is betterKimi K3.1 Pro: 70%Kimi K3: 71.3%Vals AIAs of 10/26/2026
Vals IndexCode Migration v1.1 · higher is betterKimi K3.1 Pro: 59.7%Kimi K3: 22.7%Vals AIAs of 10/27/2026
Vals Legal IndexBusiness & Commercial · higher is betterKimi K3.1 Pro: 59.8%Kimi K3: 66.5%Vals AIAs of 10/26/2026
BioMysteryBenchHuman-solvable · higher is betterKimi K3.1 Pro: 86.3%Kimi K3: 79.9%Vals AIAs of 10/24/2026
Finance Agent v2.1All-Pass · higher is betterKimi K3.1 Pro: 48.4%Kimi K3: 47.3%Vals AIAs of 10/26/2026
HLAB-Vals-1.1Antitrust Competition · Task fully resolved · higher is betterKimi K3.1 Pro: 0%Kimi K3: 0%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterKimi K3.1 Pro: 81.9%Kimi K3: 89.3%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterKimi K3.1 Pro: 58%Kimi K3: 68.8%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceEngineering Sciences · higher is betterKimi K3.1 Pro: 22.2%Kimi K3: 0%Vals AIAs of 10/25/2026
Vals Finance IndexFinance Agent v2.1 · higher is betterKimi K3.1 Pro: 61.5%Kimi K3: 60%Vals AIAs of 10/26/2026
Vals Legal IndexCivil Negligence · higher is betterKimi K3.1 Pro: 62.4%Kimi K3: 68.6%Vals AIAs of 10/26/2026
Finance Agent v2.1Comparables · higher is betterKimi K3.1 Pro: 63.9%Kimi K3: 59.2%Vals AIAs of 10/26/2026
HLAB-Vals-1.1Arbitration International Dispute Resolution · Criteria passed · higher is betterKimi K3.1 Pro: 94.1%Kimi K3: 93.9%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterKimi K3.1 Pro: 27.9%Kimi K3: 39.5%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterKimi K3.1 Pro: 36.7%Kimi K3: 45.7%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceLife Sciences · higher is betterKimi K3.1 Pro: 36.8%Kimi K3: 0%Vals AIAs of 10/25/2026
Vals Finance IndexTax Agent Bench · higher is betterKimi K3.1 Pro: 24.9%Kimi K3: 33.4%Vals AIAs of 10/26/2026
Vals IndexFinance Agent v2.1 · higher is betterKimi K3.1 Pro: 61.5%Kimi K3: 60%Vals AIAs of 10/27/2026
Finance Agent v2.1Disclosure Analysis · higher is betterKimi K3.1 Pro: 70.1%Kimi K3: 71.6%Vals AIAs of 10/26/2026
HLAB-Vals-1.1Arbitration International Dispute Resolution · Task fully resolved · higher is betterKimi K3.1 Pro: 10%Kimi K3: 10%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterKimi K3.1 Pro: 66.3%Kimi K3: 83.5%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterKimi K3.1 Pro: 64.8%Kimi K3: 72.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterKimi K3.1 Pro: 55.6%Kimi K3: 11.1%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceMathematical Sciences · higher is betterKimi K3.1 Pro: 23.5%Kimi K3: 0%Vals AIAs of 10/25/2026
Finance Agent v2.1Earnings Analysis · higher is betterKimi K3.1 Pro: 78%Kimi K3: 80.4%Vals AIAs of 10/26/2026
HLAB-Vals-1.1Banking Finance · Criteria passed · higher is betterKimi K3.1 Pro: 94.4%Kimi K3: 92.7%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterKimi K3.1 Pro: 29.6%Kimi K3: 44.4%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterKimi K3.1 Pro: 27.9%Kimi K3: 32.6%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterKimi K3.1 Pro: 73.8%Kimi K3: 9.5%Vals AIAs of 10/26/2026