Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-4o mini | Mistral Small (Sep '24) |
|---|---|---|
| Input ($/M tokens) | $0.15 | $0.2 |
| Output ($/M tokens) | $0.6 | $0.6 |
Verdict. GPT-4o mini wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Mistral Small (Sep '24) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Mistral Small (Sep '24) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. GPT-4o mini is strongest on Coding Index (11.4), Intelligence Index (6.7). Mistral Small (Sep '24) leads on Intelligence Index (4.3).
Speed. On throughput, Mistral Small (Sep '24) generates tokens at 143 tok/s versus 101 tok/s — about 29% faster. On time-to-first-token, Mistral Small (Sep '24) responds in 810ms vs 1030ms, which matters most for chat-style UIs.
Provider. OpenAI and Mistral sell to overlapping but distinct developer audiences: OpenAI tends to ship frontier reasoning models with premium positioning, while Mistral often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): GPT-4o mini costs $13.50 ($162/year); Mistral Small (Sep '24) costs $15.00 ($180/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): GPT-4o mini ≈ $1.95/run, Mistral Small (Sep '24) ≈ $2.20/run. At agent/realtime scale (200M input / 100M output per million requests): GPT-4o mini ≈ $90/run, Mistral Small (Sep '24) ≈ $100/run. GPT-4o mini becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
GPT-4o mini is cheaper overall. Its blended price (3:1 input/output ratio) is $0.26/M tokens vs $0.30/M for Mistral Small (Sep '24).
GPT-4o mini wins 2 out of 12 benchmarks compared to 0 for Mistral Small (Sep '24). See the detailed benchmark chart above for per-category results.
Mistral Small (Sep '24) generates tokens faster at 143 tok/s vs 101 tok/s. However, Mistral Small (Sep '24) has lower time-to-first-token (0.81s vs 1.03s).
Choose based on your priorities: GPT-4o mini for lower cost, GPT-4o mini for stronger benchmark performance, and Mistral Small (Sep '24) for faster generation. For latency-sensitive apps, check the TTFT comparison above.