Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Codestral Embed 2505 vs Devstral 2 2512

Short answer

Codestral Embed 2505 ($0.15 in / $0 out); Devstral 2 2512 ($0.40 in / $2.00 out). Lowest listed input price: Codestral Embed 2505. Longest listed context: Devstral 2 2512 at 262,144 tokens. A lower price is not a quality ranking.

Side-by-side facts. The third-party index is copied when the feed has one. Unknown means it did not.
FactCodestral Embed 2505Devstral 2 2512
LabMistralMistral
KindEmbeddingsChat
Listed30 Oct 20259 Dec 2025
Context8,192262,144
Input / million$0.15$0.40
Output / million$0$2.00
Batch inputNot listedNot listed
Batch outputNot listedNot listed
Inputstextfile, text
Outputsembeddingstext
ToolsNot listedYes
Open weightsNo public weights id listedYes
Knowledge cutoffUnknownUnknown
Third-party indexUnknownUnknown
GuideNew, not yet reviewedReviewed

Input and output prices are USD per million tokens, from pricing.prompt and pricing.completion. The index is not our benchmark.

Codestral Embed 2505

New, not yet reviewed. No guide note yet.

Codestral Embed 2505 is listed at $0.15 input and $0 output per million tokens, with a 8,192-token context window.

Devstral 2 2512

OpenRouter describes Devstral 2 as Mistral's open-weight coding model for agentic work, including exploring a repository. Text and file input, text output, a 256,000-token window. It is a coding tool, not a general writer.

Devstral 2 2512 is listed at $0.40 input and $2.00 output per million tokens, with a 262,144-token context window.

Choose models

Popular comparisons