← Compare models
Open all in the calculator — adjust volume and token counts →
Mercury 3 vs Llama 4 Maverick
List-price comparison ·Mercury 3 details ·Llama 4 Maverick details
For a typical workload (100,000 requests / mo), Mercury 3 is the cheapest — 47% less than the priciest here ($26.00/mo vs $48.60/mo).
| Mercury 3 | Llama 4 Maverick | |
|---|---|---|
| Input / 1M tokens | $0.100 | $0.188 |
| Output / 1M tokens | $0.350 | $0.652 |
| Typical request (1,200 in + 400 out) | $0.0003 | $0.0005 |
| Context window | 1M tokens | 524,288 tokens |
| Max output | 131,072 tokens | 16,384 tokens |
| Quality score | 68/100 | 74/100 |
| Tier | Balanced | Balanced |
| Provider | Inception | Meta |
Projected monthly cost
| Requests / mo | Mercury 3 | Llama 4 Maverick |
|---|---|---|
| 1,000 | $0.26 | $0.486 |
| 10,000 | $2.60 | $4.86 |
| 100,000 | $26.00 | $48.60 |
Mercury 3
Auto-synced from OpenRouter — no editorial write-up yet.
Llama 4 Maverick
Strong multi-modal (text + image) open-weight model with a 1M-token context window — good for self-hosted or fine-tuned deployments.
Smaller completion-token cap (16K) than newer commercial models limits very long single-turn outputs — chunk long generations.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.