Compare OpenAI Codex Mini by OpenAI against Kimi K2.5 by Moonshot AI, context windows of 200K vs 262K, tested across 10 shared challenges. Updated April 2026.
OpenAI Codex Mini and Kimi K2.5 are both competitive models. OpenAI Codex Mini costs $1.5/M input tokens vs $0.6/M for Kimi K2.5. Context windows: 200K vs 262K tokens. Compare their real outputs side by side below.
OpenAI Codex Mini is made by openai while Kimi K2.5 is from moonshotai. OpenAI Codex Mini has a 200K token context window compared to Kimi K2.5's 262K. On pricing, OpenAI Codex Mini costs $1.5/M input tokens vs $0.6/M for Kimi K2.5.
No community votes yet. On paper, Kimi K2.5 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 Kimi K2.5 by Moonshot AI, context windows of 200K vs 262K, tested across 10 shared challenges. Updated April 2026.
OpenAI Codex Mini and Kimi K2.5 are both competitive models. OpenAI Codex Mini costs $1.5/M input tokens vs $0.6/M for Kimi K2.5. Context windows: 200K vs 262K tokens. Compare their real outputs side by side below.
OpenAI Codex Mini is made by openai while Kimi K2.5 is from moonshotai. OpenAI Codex Mini has a 200K token context window compared to Kimi K2.5's 262K. On pricing, OpenAI Codex Mini costs $1.5/M input tokens vs $0.6/M for Kimi K2.5.
No community votes yet. On paper, Kimi K2.5 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.
