Mistral Small 3.2 vs Ministral 14B: Pricing Comparison
Compare pricing, capabilities, and costs for your LLM workloads.
Mistral
Mistral Small 3.2
Pricing (per 1M tokens)
Input$0.0750
Output$0.2000
Cached Input$0.0100
Context & Output
Context Window131.1K tokens
Max Output32.8K tokens
Capabilities
Categorybudget
Multimodaltext
Fine-tuningNo
StreamingYes
Mistral
Ministral 14B
Pricing (per 1M tokens)
Input$0.2000
Output$0.2000
Cached Input$0.0200
Context & Output
Context Window262.1K tokens
Max Output16.4K tokens
Capabilities
Categorybudget
Multimodaltext
Fine-tuningNo
StreamingYes
Quick Verdict
Cheaper Input Price
Mistral Small 3.2
62.5% cheaper
Cheaper Output Price
Ministral 14B
0.0% cheaper
Larger Context Window
Ministral 14B
+131.1K tokens
Cost Comparison
Sample workload: 1,000,000 input tokens + 1,000,000 output tokens
Mistral Small 3.2
$0.2750
$0.0750/1M input + $0.2000/1M output
Ministral 14B
$0.4000
$0.2000/1M input + $0.2000/1M output
Mistral Small 3.2 is 31.3% cheaper for this workload.
Frequently Asked Questions
Which is cheaper, Mistral Small 3.2 or Ministral 14B?
For input tokens, Mistral Small 3.2 is cheaper at $0.0750 per 1M tokens. For output tokens, Ministral 14B is cheaper at $0.2000 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of Mistral Small 3.2 vs Ministral 14B?
Mistral Small 3.2 has a context window of 131.1K tokens, while Ministral 14B has 262.1K tokens. Ministral 14B supports a larger context window of 262.1K tokens, which is beneficial for processing longer documents.
Need more tools?
Explore our complete suite of LLM calculators and comparison tools.