Kimi K3.1 Provs.Kimi K2.6
Is the higher price worth it?
If you need top performance, yes: Kimi K3.1 Pro is clearly ahead in the overall index and costs 2.1 times (input) and 2.5 times (output) as much per token.
80
Kimi K3.1 Pro
Rank 10 to 13
15
Kimi K2.6
Rank 46 to 52
36
Kimi K3.1 Pro
slow
58
Kimi K2.6
slow
$4
Kimi K3.1 Pro
fairly expensive
$1.71
Kimi K2.6
fairly 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 K2.6
- 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). 21 plans in Germany.
- Via API
$0.95 input, $4 output per 1M tokens according to the provider; the price index has listed it at $0.75 and $3.50 since Sep 18, 2026.
- Note
- There is a successor: Kimi K3 (rank 18 to 24, $3 input, $15 output).
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: 8Kimi K2.6 ahead: 0level: 0too little data: 2of 10 areas
AreaKimi K3.1 ProKimi K2.60 to 100, higher is betterResult
Areas in the overall index
CodingKimi K3.1 Pro aheadKimi K3.1 Pro: 85Kimi K2.6: 12
ReasoningKimi K3.1 Pro aheadKimi K3.1 Pro: 80Kimi K2.6: 16
Mathematicsonly Kimi K3.1 Pro has a scoreKimi K3.1 Pro: 81Kimi K2.6: not enough data
KnowledgeKimi K3.1 Pro aheadKimi K3.1 Pro: 85Kimi K2.6: 17
AgentsKimi K3.1 Pro aheadKimi K3.1 Pro: 80Kimi K2.6: 14
GeneralKimi K3.1 Pro aheadKimi K3.1 Pro: 74Kimi K2.6: 19
MultimodalKimi K3.1 Pro aheadKimi K3.1 Pro: 75Kimi K2.6: 28
Specialist fields
FinanceKimi K3.1 Pro aheadKimi K3.1 Pro: 62Kimi K2.6: 18
LegalKimi K3.1 Pro aheadKimi K3.1 Pro: 68Kimi K2.6: 10
Healthonly Kimi K2.6 has a scoreKimi K3.1 Pro: not enough dataKimi K2.6: 9
Show 1 more areas that do not count toward the overall index
AreaKimi K3.1 ProKimi K2.60 to 100, higher is betterResult
Productivityonly Kimi K2.6 has a scoreKimi K3.1 Pro: not enough dataKimi K2.6: 8
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 K2.6
Output withheld for safety
Reasoning (requested): high
Current attempt
- Run date
- Oct 5, 2026
- API provider
- openrouter
- Requested API model
- moonshotai/kimi-k2.6
- API model reported in response
- moonshotai/kimi-k2.6
- Reasoning setting
- high
- Pinned endpoint
- Moonshot AI | moonshotai/kimi-k2.6-20260420
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Failed
- Response time
- 124 s
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Earlier attempts (3)
- Oct 2, 2026Output withheld for safetyReasoning setting: high
- Oct 1, 2026Output withheld for safetyReasoning setting: high
- 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 K2.6 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 80 | 15 |
| Rank | Rank 10 to 13 of 95 | Rank 46 to 52 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $2 | $0.95 |
| Outputwhat the model writes | $10 | $4 |
| Speed | ||
| Tokens per second | 36 | 58 |
| Technical | ||
| Context windowhow much text the model reads at once | 1.05 M tokens≈ 1,570 A4 pages | 262,144 tokens≈ 390 A4 pages |
| Knowledge cutoff | n/a | n/a |
| Released | Oct 23, 2026 | Apr 20, 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 K2.6
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 37.5%Kimi K2.6: 15.9%Vals AIAs of 10/26/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 24.9%Kimi K2.6: 12.4%Vals AIAs of 10/26/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 84.9%Kimi K2.6: 37.9%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 56.1%Kimi K2.6: 18.2%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 10%Kimi K2.6: 3.3%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 81.9%Kimi K2.6: 75.5%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 58%Kimi K2.6: 42.3%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 27.9%Kimi K2.6: 20.9%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 36.7%Kimi K2.6: 26.5%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 66.3%Kimi K2.6: 78.4%Vals AIAs of 10/26/2026
Show 23 more benchmarks
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 64.8%Kimi K2.6: 51.2%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 29.6%Kimi K2.6: 18.5%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 27.9%Kimi K2.6: 9.3%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 75.8%Kimi K2.6: 75.8%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 68.8%Kimi K2.6: 46.7%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 31.6%Kimi K2.6: 21.1%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 13.3%Kimi K2.6: 3.3%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 74.5%Kimi K2.6: 79.2%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 61.9%Kimi K2.6: 37.6%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 28.1%Kimi K2.6: 14%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 30%Kimi K2.6: 23.3%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 69.7%Kimi K2.6: 75.1%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 72.9%Kimi K2.6: 61.8%Vals AIAs of 10/26/2026
Legal Research BenchFamily · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 13.6%Kimi K2.6: 0%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 30%Kimi K2.6: 10%Vals AIAs of 10/26/2026
Legal Research BenchFamily · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 63.6%Kimi K2.6: 61%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 53.8%Kimi K2.6: 30.4%Vals AIAs of 10/26/2026
Legal Research BenchHealth · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 73.3%Kimi K2.6: 30%Vals AIAs of 10/26/2026
Tax Agent BenchWeighted Pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 63.7%Kimi K2.6: 45.1%Vals AIAs of 10/26/2026
Legal Research BenchHealth · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 90.5%Kimi K2.6: 81.7%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 18.2%Kimi K2.6: 18.2%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 32.7%Kimi K2.6: 75.6%Vals AIAs of 10/26/2026
Legal Research BenchOverall · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 71.4%Kimi K2.6: 74.7%Vals AIAs of 10/26/2026