modelgrep

Longest-Context LLMs

Match · Updated July 2026

Grok 4.20 Multi-Agent has the largest context window of any LLM, at 2M tokens. Grok 4.20 (2M) and Llama 4 Scout (1.3M) round out the top three.

2MContext
$1.25Input /M

AI models with the largest context windows, ranked by token capacity. The best large language models for long documents, codebases and extended conversations.

  1. 1x-ai logo
    grok-4.20-multi-agent
    ReasoningJSONVision$1.25/M
    2M
    Context
  2. 2x-ai logo
    grok-4.20
    ReasoningToolsJSON+137.0 intel · $1.25/M
    2M
    Context
  3. 3meta-llama logo
    llama-4-scout
    ToolsJSONVision10.0 intel · $0.100/M
    1.3M
    Context
  4. 4openai logo
    gpt-5.6-luna-pro
    ReasoningToolsJSON+1$0.100/M
    1.1M
    Context
  5. 5openai logo
    gpt-5.6-luna
    ReasoningToolsJSON+151.2 intel · $0.100/M
    1.1M
    Context
  6. 6openai logo
    gpt-5.6-terra-pro
    ReasoningToolsJSON+1$1.00/M
    1.1M
    Context
  7. 7openai logo
    gpt-5.6-terra
    ReasoningToolsJSON+155.0 intel · $1.00/M
    1.1M
    Context
  8. 8openai logo
    gpt-5.6-sol-pro
    ReasoningToolsJSON+1$5.00/M
    1.1M
    Context
  9. 9openai logo
    gpt-5.6-sol
    ReasoningToolsJSON+158.9 intel · $5.00/M
    1.1M
    Context
  10. 10openai logo
    gpt-5.5-pro
    ReasoningToolsJSON+1$30.00/M
    1.1M
    Context
  11. 11openai logo
    gpt-5.5
    ReasoningToolsJSON+154.8 intel · $5.00/M
    1.1M
    Context
  12. 12openai logo
    gpt-5.5:batch
    ReasoningToolsJSON+154.8 intel · $2.50/M
    1.1M
    Context
  13. 13xiaomi logo
    mimo-v2.5-pro
    ReasoningToolsJSON42.2 intel · $0.435/M
    1.1M
    Context
  14. 14xiaomi logo
    mimo-v2.5
    ReasoningToolsJSON+237.2 intel · $0.140/M
    1.1M
    Context
  15. 15openai logo
    gpt-5.4-pro
    ReasoningToolsJSON+1$30.00/M
    1.1M
    Context
  16. 16openai logo
    gpt-5.4
    ReasoningToolsJSON+151.4 intel · $2.50/M
    1.1M
    Context
  17. 17openai logo
    gpt-5.4:batch
    ReasoningToolsJSON+151.4 intel · $1.25/M
    1.1M
    Context
  18. 18M
    longcat-2.0
    ReasoningTools33.5 intel · $0.300/M
    1.0M
    Context
  19. 19P
    laguna-s-2.1
    ReasoningTools$0.100/M
    1.0M
    Context
  20. 20google logo
    gemini-3.6-flash
    ReasoningToolsJSON+250.1 intel · $1.50/M
    1.0M
    Context
  21. 21google logo
    gemini-3.6-flash:batch
    ReasoningToolsJSON+250.1 intel · $0.750/M
    1.0M
    Context
  22. 22google logo
    gemini-3.5-flash-lite
    ReasoningToolsJSON+236.5 intel · $0.300/M
    1.0M
    Context
  23. 23google logo
    gemini-3.5-flash-lite:batch
    ReasoningToolsJSON+236.5 intel · $0.150/M
    1.0M
    Context
  24. 24T
    inkling
    ReasoningToolsJSON+240.7 intel · $1.00/M
    1.0M
    Context
  25. 25moonshotai logo
    kimi-k3
    ReasoningToolsJSON+157.1 intel · $3.00/M
    1.0M
    Context

Frequently asked

Which LLM has the largest context window?

Grok 4.20 Multi-Agent has the largest context window of any LLM, at 2M tokens. Grok 4.20 (2M) and Llama 4 Scout (1.3M) round out the top three.

Which AI model has the biggest context window?

Grok 4.20 Multi-Agent has the largest context window of any AI model, at 2M tokens. Grok 4.20 (2M) and Llama 4 Scout (1.3M) round out the top three.

What's a good alternative to Grok 4.20 Multi-Agent?

Grok 4.20 (2M) is the closest alternative on this metric, followed by Llama 4 Scout (1.3M). See the full ranking above for the tradeoffs.

By maker

All rankings