Side-by-side comparison
Mercury 2 vs Llama 3.1 70B Instruct
Meta
Llama 3.1 70B Instruct
🔧 Tools
{} JSON
Input / 1M
$0.4000
Output / 1M
$0.4000
| Mercury 2 | Llama 3.1 70B Instruct | |
|---|---|---|
| Provider | Inception | Meta |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 128,000 | 131,072 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.2500 | 0.4000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.7500 | 0.4000 |
Frequently asked questions
Which is cheaper, Mercury 2 or Llama 3.1 70B Instruct?
Llama 3.1 70B Instruct is cheaper than Mercury 2 on a 50/50 input/output blend by about $0.1 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Mercury 2 or Llama 3.1 70B Instruct?
Llama 3.1 70B Instruct has the larger context window at 131k tokens versus 128k tokens for Mercury 2. That means Llama 3.1 70B Instruct can ingest about 1.0x as much text per request.
What is the difference between Mercury 2 and Llama 3.1 70B Instruct?
Mercury 2 comes from Inception; Llama 3.1 70B Instruct comes from Meta. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.