Llama 4 Scout vs Mercury 3
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Llama 4 Scout is 8% cheaper than Mercury 3 on a typical 3:1 input/output mix. Llama 4 Scout has the larger context window (1.3M vs 1M).
| Llama 4 Scout | Mercury 3 | |
|---|---|---|
| Input price / 1M | $0.10 | $0.10 |
| Output price / 1M | $0.30 | $0.35 |
| Blended price (3:1) | $0.15 | $0.16 |
| Cached input / 1M | — | $0.01 |
| Context window | 1.3M | 1M |
| Max output | 16K | 131K |
| Intelligence index | — | — |
| Coding index | 8.2 | — |
| Providers | 4 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | No |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
| Released | 2025-04-05 | 2026-10-16 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Llama 4 Scout or Mercury 3?
Llama 4 Scout is 8% cheaper than Mercury 3 on a typical 3:1 input/output mix.
Llama 4 Scout vs Mercury 3: which has a bigger context window?
Llama 4 Scout: 1,310,720 tokens. Mercury 3: 1,000,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Llama 4 Scout ≈ $350.00, Mercury 3 ≈ $375.00.
More comparisons
Llama 4 Scout vs GPT-6.1 TerraLlama 4 Scout vs GPT-6.1 Terra ProLlama 4 Scout vs Kimi K3.1 ProLlama 4 Scout vs MiniMax M3.1 FlashLlama 4 Scout vs DeepSeek V4.1 Flash 1017Llama 4 Scout vs Nemotron 3.5 Super VLLlama 4 Scout vs Gemini 4 ArgonLlama 4 Scout vs Claude Haiku 5.5Llama 4 Scout vs Nano Banana 2.1Llama 4 Scout vs Mistral Large 4Llama 4 Scout vs GPT-6.1 Sol ProLlama 4 Scout vs GPT-6.1 SolLlama 4 Scout vs Claude Sonnet 5.5Llama 4 Scout vs GLM 5.3 PrimeLlama 4 Scout vs Qwen3.8 Max PrimeLlama 4 Scout vs Command A+Mercury 3 vs GPT-6.1 TerraMercury 3 vs GPT-6.1 Terra ProMercury 3 vs Kimi K3.1 ProMercury 3 vs MiniMax M3.1 FlashMercury 3 vs DeepSeek V4.1 Flash 1017Mercury 3 vs Nemotron 3.5 Super VLMercury 3 vs Gemini 4 ArgonMercury 3 vs Claude Haiku 5.5