Grok 3 vs Grok 3 mini
xAI vs xAI · Prices checked 12 August 2026
On blended cost Grok 3 mini undercuts Grok 3 by about 18.3×: $0.360 per million tokens versus $6.60. A single 100K-input, 10K-output job costs $0.035 on Grok 3 mini against $0.450 on Grok 3.
Of the 5 shared benchmarks, Grok 3 takes 5. The widest gap is on LMArena Elo, where Grok 3 leads by 67 points. Context is level at 131,000 tokens on each side.
Pricing and capacity
| Metric | Grok 3 | Grok 3 mini | Difference |
|---|---|---|---|
| Input / 1M tokens | $3.00 | $0.300 | 10.0× |
| Output / 1M tokens | $15.00 | $0.500 | 30.0× |
| Blended · 70/30calculated | $6.60 | $0.360 | 18.3× |
| Blended · 50/50calculated | $9.00 | $0.400 | 22.5× |
| Blended · 80/20calculated | $5.40 | $0.340 | 15.9× |
| Blended · 20/80calculated | $12.60 | $0.460 | 27.4× |
| Job cost · 100K + 10Kcalculated | $0.450 | $0.035 | 12.9× |
| Job cost · 1M + 100Kcalculated | $4.50 | $0.350 | 12.9× |
| Context window | 131,000 | 131,000 | level |
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 | Grok 3 mini | Leader |
|---|---|---|---|
| MMLU | 86% | 79% | Grok 3 |
| GPQA Diamond | 75% | 64% | Grok 3 |
| MATH | 89% | 81% | Grok 3 |
| HumanEval | 86% | 78% | Grok 3 |
| LMArena Elo | 1332 Elo | 1265 Elo | Grok 3 |
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.
What each model is for
Grok 3
xAI · Frontier
xAI's flagship Grok. Real-time access to the X firehose makes it strong on current events and live commentary.
- Real-time X data
- Less filtered tone
- Strong general reasoning
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
Frequently asked questions
Which is cheaper, Grok 3 or Grok 3 mini?
On blended cost Grok 3 mini undercuts Grok 3 by about 18.3×: $0.360 per million tokens versus $6.60. A single 100K-input, 10K-output job costs $0.035 on Grok 3 mini against $0.450 on Grok 3. 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 or Grok 3 mini?
Of the 5 shared benchmarks, Grok 3 takes 5. The widest gap is on LMArena Elo, where Grok 3 leads by 67 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 or Grok 3 mini?
Context is level at 131,000 tokens on each side. 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 and Grok 3 mini 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.