Kimi K2 Thinking

AI model Released Nov 6, 2025

Context window: 262,144 tokens
Maximum output: 262,144 tokens
Open weights: Yes

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Kimi K2 Thinking 145.9^* Kimi K2 Thinking · 95% interval 143.3–147.4

Run it locally

Inference · memory estimate

Kimi K2 Thinking

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Kimi K2 Thinking

Provider offer

Kimi K2 Thinking / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
AWS BedrockKimi K2 ThinkingStandard Global cross-region	Input	USD	0.6 / 1M tokens
AWS BedrockKimi K2 ThinkingStandard Global cross-region	Output	USD	2.5 / 1M tokens

Capabilities

Context window: 262,144 tokens
Maximum output: 262,144 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2024-08
Model license: other

Input modalities

text

Output modalities

text

Processing & platform

Architecture: kimi_k2

* Provisional data