Coding

Writing, refactoring and reviewing source code, including agentic edits across several files in a repository.

Router mapuje zadanie na modele kandydujące, a następnie stosuje twoją politykę: najpierw region, potem cena, a potem model z lepiej udokumentowanym wynikiem.

Prefer a code-specialised model with a published SWE-bench or agentic score; treat vendor-reported numbers as vendor-reported, and check the licence before commercial serving.

{"model":"llmeu-auto","messages":[{"role":"user","content":"…"}],"llmeu":{"task":"coding"}}

Polecane

Devstral Small 2 (24B)

Mistral AI

Nie hostowany — backend mock Otwarte wagi Europejski dostawca

Devstral Small 2 is a 24B Apache-2.0 model fine-tuned for software-engineering agents, built with All Hands AI. The model card rep…

Mistral Small 4 (119B-A6B)

Mistral AI

Nie hostowany — backend mock Otwarte wagi Europejski dostawca

Mistral Small 4 is an Apache-2.0 mixture-of-experts model with 119B total parameters and 6.5B activated per token. It accepts text…

Europejski katalog modeli

Devstral Small 2 (24B)Mistral Small 4 (119B-A6B)Codestral 25.08 DeepSeek-R1 DeepSeek-R1-Distill-Qwen-32B DeepSeek-V3.2 DeepSeek-V4-Flash (0731)GLM-4.7-Flash GLM-5.3 Gemma 4 26B A4B IT Gemma 4 31B IT Magistral Small 1.2