Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of codestral-embed, Krea: K3 Edit, VoyageAI by MongoDB: voyage-4-lite
3 modelsUnknowncodestral-embedRemove ×kreaKrea: K3 EditRemove ×voyageaiVoyageAI by MongoDB: voyage-4-liteRemove ×
What’s different8.2K contextEdits one to eight reference images from a text prompt, returning one image.voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings in 2048,…
DateOct 16, 2026DiscoveredOct 15, 2026ListedJul 27, 2026Listed
Listed rate$0.15 in / $0.00 out/ 1M tokensExperiential · all routes ↗Standard list rateSee provider quotes$0.02 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints1 endpoint →0 endpoints →1 endpoint →
Context window8.2K65.5K32K
Max output—59K28.8K
Parameters———
Image inputNot reportedSupportedNot reported

Add another model

Search all models →