Side-by-side comparison
Gemma 3 12B vs Mistral Small 3.2 24B
Google
Gemma 3 12B
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$0.0400
Output / 1M
$0.1300
Mistral
Mistral Small 3.2 24B
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$0.0750
Output / 1M
$0.2000
| Gemma 3 12B | Mistral Small 3.2 24B | |
|---|---|---|
| Provider | Mistral | |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 128,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools, json_mode | vision, tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.0400 | 0.0750 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.1300 | 0.2000 |
Frequently asked questions
Which is cheaper, Gemma 3 12B or Mistral Small 3.2 24B?
Gemma 3 12B is cheaper than Mistral Small 3.2 24B on a 50/50 input/output blend by about $0.0525 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, Gemma 3 12B or Mistral Small 3.2 24B?
Gemma 3 12B has the larger context window at 131k tokens versus 128k tokens for Mistral Small 3.2 24B. That means Gemma 3 12B can ingest about 1.0x as much text per request.
What is the difference between Gemma 3 12B and Mistral Small 3.2 24B?
Gemma 3 12B comes from Google; Mistral Small 3.2 24B 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.