Usage rankings

Languages

Languages · Korean proxy

Not Korean-specific

The stable API does not expose a Korean-specific ranking. This is the Translation use-case order, not natural-language share.

  1. 1
    DeepSeek: DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017
    #1
  2. 2
    DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
    #2
  3. 3
    Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash
    #3
  4. 4
    OpenAI: GPT-6 Lunaopenai/gpt-6-luna
    #4
  5. 5
    DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731
    #5
  6. 6
    TypeSafe: Jev 1.13typesafe/jev-1.13
    #6
  7. 7
    Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5
    #7
  8. 8
    DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash
    #8

Scope and sources

LastAI uses documented stable APIs only. The 10K context bucket, tool-using requests, and image-input activity are shown as observed token floors. Korean or Python-specific tags, tool-call counts, and image counts lack stable APIs, so proxies are separated and never used in a composite score.

Source: OpenRouter (openrouter.ai/rankings), as of 2026-11-12T05:20:08.915Z.

Methodology · external sources

You