Compare GPT-5.1-Codex-Mini by OpenAI against Horizon Beta by OpenRouter, context windows of 400K vs 256K, tested across 41 shared challenges. Updated April 2026.
GPT-5.1-Codex-Mini and Horizon Beta are both competitive models. GPT-5.1-Codex-Mini costs $1.5/M input tokens vs $0/M for Horizon Beta. Context windows: 400K vs 256K tokens. Compare their real outputs side by side below.
GPT-5.1-Codex-Mini is made by openai while Horizon Beta is from openrouter. GPT-5.1-Codex-Mini has a 400K token context window compared to Horizon Beta's 256K. On pricing, GPT-5.1-Codex-Mini costs $1.5/M input tokens vs $0/M for Horizon Beta.
No community votes yet. On paper, GPT-5.1-Codex-Mini has the edge — bigger model tier, newer, bigger context window, major provider backing.
GPT-5.1-Codex-Mini uses 332.9x more bold
Ask them anything yourself
Some models write identically. You are paying for the brand.
178 models fingerprinted across 32 writing dimensions. Free research.
185x
price gap between models that write identically
178
models
12
clone pairs
32
dimensions
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.

Compare GPT-5.1-Codex-Mini by OpenAI against Horizon Beta by OpenRouter, context windows of 400K vs 256K, tested across 41 shared challenges. Updated April 2026.
GPT-5.1-Codex-Mini and Horizon Beta are both competitive models. GPT-5.1-Codex-Mini costs $1.5/M input tokens vs $0/M for Horizon Beta. Context windows: 400K vs 256K tokens. Compare their real outputs side by side below.
GPT-5.1-Codex-Mini is made by openai while Horizon Beta is from openrouter. GPT-5.1-Codex-Mini has a 400K token context window compared to Horizon Beta's 256K. On pricing, GPT-5.1-Codex-Mini costs $1.5/M input tokens vs $0/M for Horizon Beta.
No community votes yet. On paper, GPT-5.1-Codex-Mini has the edge — bigger model tier, newer, bigger context window, major provider backing.
GPT-5.1-Codex-Mini uses 332.9x more bold
Ask them anything yourself
Some models write identically. You are paying for the brand.
178 models fingerprinted across 32 writing dimensions. Free research.
185x
price gap between models that write identically
178
models
12
clone pairs
32
dimensions
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.
