Compare Mistral Medium 3.1 and Mistral Small 4, both from Mistral AI, context windows of 131K vs 262K, tested across 53 shared challenges. Updated April 2026.
Mistral Medium 3.1 and Mistral Small 4 are both competitive models. Mistral Medium 3.1 costs $0.4/M input tokens vs $0.15/M for Mistral Small 4. Context windows: 131K vs 262K tokens. Compare their real outputs side by side below.
Mistral Medium 3.1 is made by mistral while Mistral Small 4 is from mistral. Mistral Medium 3.1 has a 131K token context window compared to Mistral Small 4's 262K. On pricing, Mistral Medium 3.1 costs $0.4/M input tokens vs $0.15/M for Mistral Small 4.
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Mistral Small 4 is 3.3x cheaper per token — worth considering if cost matters.
Mistral Medium 3.1 uses 2.1x more emoji
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 Mistral Medium 3.1 and Mistral Small 4, both from Mistral AI, context windows of 131K vs 262K, tested across 53 shared challenges. Updated April 2026.
Mistral Medium 3.1 and Mistral Small 4 are both competitive models. Mistral Medium 3.1 costs $0.4/M input tokens vs $0.15/M for Mistral Small 4. Context windows: 131K vs 262K tokens. Compare their real outputs side by side below.
Mistral Medium 3.1 is made by mistral while Mistral Small 4 is from mistral. Mistral Medium 3.1 has a 131K token context window compared to Mistral Small 4's 262K. On pricing, Mistral Medium 3.1 costs $0.4/M input tokens vs $0.15/M for Mistral Small 4.
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Mistral Small 4 is 3.3x cheaper per token — worth considering if cost matters.
Mistral Medium 3.1 uses 2.1x more emoji
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.

48 fights queued
36+ more head-to-head results. Free. Not a trick.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy Policy
48 fights queued
36+ more head-to-head results. Free. Not a trick.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy Policy