Kimi K3

New

moonshotai/kimi-k3-20260715

  • tool use
  • structured outputs
  • reasoning

At a glance

providermoonshotai
releasedJul 16, 2026
context1.0M
input / M$3

Specifications

What the API gives you

Context window
1.0M tokens
Max output
—
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Cache read
$0.30 / 1M tokens
Modalities
text, image → text
Knowledge cutoff
—
Released
Jul 16, 2026

Recommendation coverage

Where this model appears

  1. #1Best LLM for RAG & Long Context
  2. #1Best LLM for Coding
  3. #1Best LLM for Frontend & UI
  4. #3Best LLM for Creative Writing
  5. #4Best LLM for Writing
  6. #4Best Cheap LLM for High Volume
  7. #6Best LLM for Chat & Roleplay
  8. #6Best LLM for Translation
  9. #7Best LLM for Document Summarization
  10. #7Best LLM for Everyday Translation
  11. #7Best LLM for Roleplay & Character

Measured evidence

Public benchmark record

LMArena Agent
9.62026-07-20
LMArena Text
1473 Elo2026-07-16
LMArena Text
1483 Elo2026-07-20
LMArena WebDev
1679 Elo2026-07-16
LMArena WebDev
1677 Elo2026-07-20

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.