kimi-k2-thinking

Name: kimi-k2-thinking
Price: 0.6 USD
Availability: InStock
Rating: 52.3 (1714 reviews)
Author: Moonshot AI

#211Large Language ModelsProprietary

Moonshot AI

Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.

Model updates refreshed4h agoOct 12, 2026news + changelog

Website View Updates Subscribe

What changed

Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.

Rates & subscription access

View full pricing details

Tracked access rates

OpenRouter

Input / 1M tokens: $0.6
Output / 1M tokens: $2.5

Price record: 2026-10-12. Source: openrouter.

Related provider subscriptions

Kimi Code MembershipPrice not verified

Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.

No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.

52.3

Quality Score

---

Arena ELO

1.0T

Parameters

256K

Context

Evidence profile

How complete is this record?

This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.

86%

coverage

Strong evidence

19 of 22 public signals

Technical profile100%

Benchmarks and Competitive Signal

Structured

Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.

This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.

HumanEvalcoding

85.3

Similar Models

Discussion (0)

Loading comments...

Research-backed technical record

Parameters

1.0T

Training compute

4.2e24 FLOP

Dataset scale

Not reported

Base model

Kimi K2

Source-reported access: Open weights (restricted use) · Likely confidence

Official Benchmark Evidence

These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.

Kimi-K2-Thinking - SWE-Bench Verified

Benchmarksswe-benchOct 12, 2026

SWE-Bench Verified resolved rate 63.4

View source

Kimi K2 Thinking Benchmark Update

Benchmarksartificial-analysisSep 18, 2026