Compare OpenAI Codex Mini by OpenAI against Horizon Beta by OpenRouter, context windows of 200K vs 256K, tested across 10 shared challenges. Updated April 2026.
OpenAI Codex Mini and Horizon Beta are both competitive models. OpenAI Codex Mini costs $1.5/M input tokens vs $0/M for Horizon Beta. Context windows: 200K vs 256K tokens. Compare their real outputs side by side below.
OpenAI Codex Mini is made by openai while Horizon Beta is from openrouter. OpenAI Codex Mini has a 200K token context window compared to Horizon Beta's 256K. On pricing, OpenAI Codex Mini costs $1.5/M input tokens vs $0/M for Horizon Beta.
No community votes yet. On paper, Horizon Beta has the edge — bigger model tier, newer.
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 OpenAI Codex Mini by OpenAI against Horizon Beta by OpenRouter, context windows of 200K vs 256K, tested across 10 shared challenges. Updated April 2026.
OpenAI Codex Mini and Horizon Beta are both competitive models. OpenAI Codex Mini costs $1.5/M input tokens vs $0/M for Horizon Beta. Context windows: 200K vs 256K tokens. Compare their real outputs side by side below.
OpenAI Codex Mini is made by openai while Horizon Beta is from openrouter. OpenAI Codex Mini has a 200K token context window compared to Horizon Beta's 256K. On pricing, OpenAI Codex Mini costs $1.5/M input tokens vs $0/M for Horizon Beta.
No community votes yet. On paper, Horizon Beta has the edge — bigger model tier, newer.
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.

10 fights queued
10 fights queued