Popular Comparisons:
⚡3-Second Selection Verdict
Daily & TestsPick Kimi k1.5 (Reasoning) (Save 34%)
Moonshot AIVerified

Kimi k1.5 (Reasoning)

★ Save 34%
Input$0.60 / 1M
Output$2.40 / 1M
Context262K
CursorBench Pass Rate—
Moonshot AIVerified

Kimi K2.6

Input$0.90 / 1M
Output$3.72 / 1M
Context262K
CursorBench Pass Rate—
Moonshot AIVerified

Kimi K3

Input$3.00 / 1M
Output$15.00 / 1M
Context1.0M
CursorBench Pass Rate—

Pick your workflow, then your budget

Estimates use our price snapshot, excluding cache, retries, taxes and tools. Check availability for preview and legacy models.

Workload cost · USD (lower costs less)

Kimi k1.5 (Reasoning)$10.80
Kimi K2.6$16.44
Kimi K3$60.00

Context capacity · tokens (not recall accuracy)

Kimi k1.5 (Reasoning)262,144
Kimi K2.6262,144
Kimi K31,048,576

CursorBench 4.0 · %

Kimi k1.5 (Reasoning)No verified data
Kimi K2.6No verified data
Kimi K3No verified data

Tool reliability, long-context recall and same-harness SWE-bench: untested, not zero.

CursorBench · 2026-10-07 ↗
Patch review example: why does an empty array slip through?

Editorial example, not measured model output. Review boundary contracts and regression tests; this is not a model ranking.

export function mean(values: number[]) {
  return values.reduce((a, b) => a + b, 0)
    / values.length;
}

// mean([]) => NaN
// Missing an explicit empty-input contract
⚙️ Select ModelKimi k1.5 (Reasoning) vs Kimi K2.6 vs Kimi K3
Slot 1Moonshot AI
Slot 2Moonshot AI
Slot 3Moonshot AI
Kimi k1.5 (Reasoning) VS Kimi K2.6 VS Kimi K3
💳 View Plans↗

💰 Monthly Cost Simulation

Simulate monthly cost differences based on your estimated token usage volume

Monthly Input Tokens (Prompt)10 M tokens
Monthly Output Tokens (Completion)2 M tokens
Kimi k1.5 (Reasoning)
$10.80/ mo
(in: $6.00 + out: $4.80)
Kimi K2.6
$16.44/ mo
(in: $9.00 + out: $7.44)
Kimi K3
$60.00/ mo
(in: $30.00 + out: $30.00)
AttributeKimi k1.5 (Reasoning)Moonshot AIKimi K2.6Moonshot AIKimi K3Moonshot AI
Input$0.60$0.90$3.00
Output$2.40$3.72$15.00
Context262K262K1.0M
CursorBench Pass Rate———
StatusVerifiedVerifiedVerified
Tags & CapabilitiesReasoning, Coding, Long context, Chain of thought, FlagshipFlagship, Reasoning, Vision, CodingFlagship, Reasoning, Coding, Long context, Open weights
LMArena Code#—#38#11
LMArena Agent#—#—#16
CursorBench#—#—#—
Artificial Analysis#—#46#18
Vals AI#—#—#26
LiveBench#—#39#12
LMArena Text#—#34#9
ADSponsored