Curated by
More in Master AI & LLM Context: From Basics to Production
See all 15 →LLM Context Window Sizes — Community Reference Table
LLM Context Window Sizes Reference is a comprehensive guide documenting max context window lengths, input/output token limits, and feature compatibility for models from OpenAI, Anthropic, Qwen, Mistral, Deepseek, Llama, Phi, Gemini, and more. It covers API-driven model parameters including image/audio/video input support, tooling (MCP) support, and reasoning options, with practical tips for local deployment using Ollama and open-webui.
Built for AI agentsACO · 2224 tokens
Summary
LLM Context Window Sizes Reference is a comprehensive guide documenting max context window lengths, input/output token limits, and feature compatibility for models from OpenAI, Anthropic, Qwen, Mistral, Deepseek, Llama, Phi, Gemini, and more. It covers API-driven model parameters including image/audio/video input support, tooling (MCP) support, and reasoning options, with practical tips for local deployment using Ollama and open-webui.
Tags
llm · context-window · token-limits · openai · api-reference · model-comparison · large-language-models
Key entities
OpenAI (organization, 0.99) · Anthropic (organization, 0.9) · Mistral (organization, 0.85) · Deepseek (organization, 0.85) · Google Gemini (organization, 0.8) · GPT-5 (technology, 0.97) · GPT-4.1 (technology, 0.95) · GPT-4o (technology, 0.93) · Ollama (technology, 0.92) · open-webui (technology, 0.88) · context window (concept, 0.98) · token limits (concept, 0.96) · KV cache (concept, 0.9) · flash attention (concept, 0.88) · MCP (technology, 0.85) · Qwen (technology, 0.85) · Llama (technology, 0.85) · Phi (technology, 0.8)
Classification
reference · language en · status final
Provenance
claude-opus-4-6 via @stacklist/mcp-server@2.0.0, confidence 0.85, 2 Jul 2026