Grok 3 mini vs Mistral Small 4
xAI vs Mistral · Prices checked 12 August 2026
On blended cost Mistral Small 4 undercuts Grok 3 mini by about 2.3×: $0.160 per million tokens versus $0.360. A single 100K-input, 10K-output job costs $0.013 on Mistral Small 4 against $0.035 on Grok 3 mini.
Of the 3 shared benchmarks, Grok 3 mini takes 3. The widest gap is on LMArena Elo, where Grok 3 mini leads by 90 points. On context, Grok 3 mini is the larger at 131,000 tokens versus 128,000.
Pricing and capacity
| Metric | Grok 3 mini | Mistral Small 4 | Difference |
|---|---|---|---|
| Input / 1M tokens | $0.300 | $0.100 | 3.0× |
| Output / 1M tokens | $0.500 | $0.300 | 40% |
| Blended · 70/30calculated | $0.360 | $0.160 | 2.3× |
| Blended · 50/50calculated | $0.400 | $0.200 | 2.0× |
| Blended · 80/20calculated | $0.340 | $0.140 | 2.4× |
| Blended · 20/80calculated | $0.460 | $0.260 | 43% |
| Job cost · 100K + 10Kcalculated | $0.035 | $0.013 | 2.7× |
| Job cost · 1M + 100Kcalculated | $0.350 | $0.130 | 2.7× |
| Context window | 131,000 | 128,000 | 2% |
Input and output rates are as published by each provider. Blended and job-cost rows are calculated comparison metrics, not published prices — how they are derived.
Benchmarks
| Benchmark | Grok 3 mini | Mistral Small 4 | Leader |
|---|---|---|---|
| MMLU | 79% | 71% | Grok 3 mini |
| HumanEval | 78% | 68% | Grok 3 mini |
| LMArena Elo | 1265 Elo | 1175 Elo | Grok 3 mini |
Only suites both models report are listed, so a missing score is never shown as a loss. Figures are provider-published or from public leaderboards and are not independently re-run. Where a model has no score of its own it inherits its base model’s, since the weights are the same.
What each model is for
Grok 3 mini
xAI · Efficient
Cheap Grok 3 sibling. Same X firehose access, smaller model behind it, good for cost-sensitive social-media tooling.
- Cheap
- Real-time X data
- Lower latency than full Grok 3
Mistral Small 4
Mistral · Efficient
Mistral's 24B small model: open-weights, fast, and strong on instruction following for its size.
- Open weights (Apache 2.0)
- Single-GPU friendly
- 128K context
Frequently asked questions
Which is cheaper, Grok 3 mini or Mistral Small 4?
On blended cost Mistral Small 4 undercuts Grok 3 mini by about 2.3×: $0.160 per million tokens versus $0.360. A single 100K-input, 10K-output job costs $0.013 on Mistral Small 4 against $0.035 on Grok 3 mini. Blended cost weights input at 70% and output at 30%; price your own token split for an exact answer, since the cheaper model on a blended basis is not always cheaper for your workload.
Which performs better, Grok 3 mini or Mistral Small 4?
Of the 3 shared benchmarks, Grok 3 mini takes 3. The widest gap is on LMArena Elo, where Grok 3 mini leads by 90 points. These are the figures each provider or public leaderboard publishes, not results we re-run, and a benchmark average can hide the specific behaviour your workload depends on.
Which has the larger context window, Grok 3 mini or Mistral Small 4?
On context, Grok 3 mini is the larger at 131,000 tokens versus 128,000. The context window caps everything in a single request: prompt, retrieved documents, conversation history and the model’s own output all share it.
Can I compare Grok 3 mini and Mistral Small 4 on my own numbers?
Yes. Open both in the side-by-side comparison tool to see every field at once, or use the token calculator to price your actual prompt and monthly request volume against each model. Both are free and need no sign-up.
Price it for your own workload
Related matchups
Terms used on this page
Prices and scores are recomputed on every deploy from the catalogue. Prices checked 12 August 2026.