Codestral Embed 2505 vs paraphrase-MiniLM-L6-v2

Compare Codestral Embed 2505 from Mistral and paraphrase-MiniLM-L6-v2 from sentence-transformers on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for mistralai
Codestral Embed 2505
Favicon for sentence-transformers
paraphrase-MiniLM-L6-v2

Overview

Codestral Embed 2505
Author
Mistral
paraphrase-MiniLM-L6-v2
Author
sentence-transformers
Codestral Embed 2505
Context length
—
paraphrase-MiniLM-L6-v2
Context length
—
Codestral Embed 2505
Reasoning
paraphrase-MiniLM-L6-v2
Reasoning
Codestral Embed 2505
Input modalities
paraphrase-MiniLM-L6-v2
Input modalities
Codestral Embed 2505
Output modalities
paraphrase-MiniLM-L6-v2
Output modalities

Analysis

Codestral Embed 2505 vs paraphrase-MiniLM-L6-v2 at a glance

Codestral Embed 2505
Input price
Not applicable
paraphrase-MiniLM-L6-v2
Input price
Not applicable
Codestral Embed 2505
Output price
Not applicable
paraphrase-MiniLM-L6-v2
Output price
Not applicable
Codestral Embed 2505
Price
$0.15/M tokens
paraphrase-MiniLM-L6-v2
Price
$0.005/M tokens
Codestral Embed 2505
Context window
Not applicable
paraphrase-MiniLM-L6-v2
Context window
Not applicable
Codestral Embed 2505
Latency (p50)
0.81 s
paraphrase-MiniLM-L6-v2
Latency (p50)
0.85 s
Codestral Embed 2505
Throughput (p50)
Not available
paraphrase-MiniLM-L6-v2
Throughput (p50)
Not available
Codestral Embed 2505
Provided by
Mistral
paraphrase-MiniLM-L6-v2
Provided by
sentence-transformers

Frequently asked questions

Is Codestral Embed 2505 cheaper than paraphrase-MiniLM-L6-v2?

paraphrase-MiniLM-L6-v2 is cheaper than Codestral Embed 2505 on OpenRouter at $0.005/M tokens for input tokens, compared with $0.15/M tokens for Codestral Embed 2505.

Which supports a longer input, Codestral Embed 2505 or paraphrase-MiniLM-L6-v2?

Codestral Embed 2505 supports a longer input at up to 8,192 tokens, compared with 512 tokens for paraphrase-MiniLM-L6-v2.

What input types do Codestral Embed 2505 and paraphrase-MiniLM-L6-v2 embed?

Codestral Embed 2505 and paraphrase-MiniLM-L6-v2 both embed text on OpenRouter.

Which is faster, Codestral Embed 2505 or paraphrase-MiniLM-L6-v2?

Codestral Embed 2505 is faster on OpenRouter with a median embedding latency of 0.81 seconds, compared with 0.85 seconds for paraphrase-MiniLM-L6-v2.