token.app › Compare › GPT-4o-mini vs Mistral Small 3
GPT-4o-mini vs Mistral Small 3
GPT-4o-mini and Mistral Small 3 split the 2 shared benchmarks evenly. Mistral Small 3 is 4.6× cheaper per token on a blended 3:1 basis. GPT-4o-mini accepts the larger context window (128K).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-4o-mini | Mistral Small 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Input $/1M | $0.150 | $0.050 |
| Output $/1M | $0.600 | $0.080 |
| Blended $/1M | $0.262 | $0.058 |
| Context window | 128K | 33K |
| Max output | 16K | 16K |
| Released | Jul 2024 | Jan 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 37.7% | 45.3% |
| OTIS Mock AIME | 6.9% | 5.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-4o-mini if…
- Higher OTIS Mock AIME (6.9% vs 5.3%)
- Larger context window (128K)
Choose Mistral Small 3 if…
- Costs less per token — $0.058 vs $0.262 blended
- Higher GPQA Diamond (45.3% vs 37.7%)
- Open weights — self-hostable
- Newer model (released Jan 2025)
FAQ
Which is better, GPT-4o-mini or Mistral Small 3?
Across the 2 benchmarks both models have independently-run scores for, GPT-4o-mini leads on 1 and Mistral Small 3 leads on 1. Benchmarks are one input — price and context window are on this page too.
Is GPT-4o-mini cheaper than Mistral Small 3?
Mistral Small 3 is cheaper: $0.058 versus $0.262 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.050. Output alone: $0.600 vs $0.080.
What context windows do GPT-4o-mini and Mistral Small 3 have?
GPT-4o-mini: 128,000 tokens. Mistral Small 3: 32,768 tokens.
Who makes GPT-4o-mini and Mistral Small 3?
GPT-4o-mini is made by OpenAI. Mistral Small 3 is made by Mistral AI.