Side-by-side comparison
Llama 3.3 70B Instruct vs Devstral Small 1.1
Meta
Llama 3.3 70B Instruct
🔧 Tools
{} JSON
Input / 1M
$0.1000
Output / 1M
$0.3200
Mistral
Devstral Small 1.1
🔧 Tools
{} JSON
Input / 1M
$0.1000
Output / 1M
$0.3000
| Llama 3.3 70B Instruct | Devstral Small 1.1 | |
|---|---|---|
| Provider | Meta | Mistral |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 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 → | 0.1000 | 0.1000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.3200 | 0.3000 |
Frequently asked questions
Which is cheaper, Llama 3.3 70B Instruct or Devstral Small 1.1?
Devstral Small 1.1 is cheaper than Llama 3.3 70B Instruct on a 50/50 input/output blend by about $0.01 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
What is the difference between Llama 3.3 70B Instruct and Devstral Small 1.1?
Llama 3.3 70B Instruct comes from Meta; Devstral Small 1.1 comes from Mistral. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.