Llama 4 Scout vs Phi-4
Meta vs Microsoft · Prices checked November 11, 2026
The two are closer than they look: Phi-4 at $0.0910 per million tokens blended, Llama 4 Scout at $0.1600, a 43 per cent difference. A single 100K-input, 10K-output job costs $0.0084 on Phi-4 against $0.0130 on Llama 4 Scout.
Pricing and capacity
RatesUSD per million tokens. Prices checked November 11, 2026.
| Metric | Llama 4 Scout | Phi-4 | Difference |
|---|---|---|---|
| Input / 1M tokens | $0.1000 | $0.0700 | 30% |
| Output / 1M tokens | $0.3000 | $0.1400 | 2.1× |
| Blended · 70/30calculated | $0.1600 | $0.0910 | 43% |
| Blended · 50/50calculated | $0.2000 | $0.1050 | 48% |
| Blended · 80/20calculated | $0.1400 | $0.0840 | 40% |
| Blended · 20/80calculated | $0.2600 | $0.1260 | 2.1× |
| Job cost · 100K + 10Kcalculated | $0.0130 | $0.0084 | 35% |
| Job cost · 1M + 100Kcalculated | $0.1300 | $0.0840 | 35% |
| Context window | 512,000 | 16,000 | 32.0× |
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.
Of the 4 shared benchmarks, Phi-4 takes 2. The widest gap is on MATH, where Phi-4 leads by 30 points. 1 suite tied. On context, Llama 4 Scout is the larger at 512,000 tokens versus 16,000.
Benchmarks
| Benchmark | Llama 4 Scout | Phi-4 | Leader |
|---|---|---|---|
| MMLU | 79.6% | 84% | Phi-4 |
| GPQA Diamond | 57.2% | 56% | Llama 4 Scout |
| MATH | 50.3% | 80% | Phi-4 |
| HumanEval | 82% | 82% | Level |
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
Llama 4 Scout
Meta · Efficient
Long-context Llama 4 with a 512K window, the open-weights answer to long-document workloads.
- 512K context
- Open weights
- MoE efficiency
Frequently asked questions
Which is cheaper, Llama 4 Scout or Phi-4?
The two are closer than they look: Phi-4 at $0.0910 per million tokens blended, Llama 4 Scout at $0.1600, a 43 per cent difference. A single 100K-input, 10K-output job costs $0.0084 on Phi-4 against $0.0130 on Llama 4 Scout. 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, Llama 4 Scout or Phi-4?
Of the 4 shared benchmarks, Phi-4 takes 2. The widest gap is on MATH, where Phi-4 leads by 30 points. 1 suite tied. 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, Llama 4 Scout or Phi-4?
On context, Llama 4 Scout is the larger at 512,000 tokens versus 16,000. 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 Llama 4 Scout and Phi-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 November 11, 2026.