Side by side

See the difference.

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

Scroll to compare models →

Comparison of text-embedding-3-small, multilingual-e5-large-instruct, Cloudflare: Clef
3 modelsUnknowntext-embedding-3-smallRemove ×intfloatmultilingual-e5-large-instructRemove ×cloudflareCloudflare: ClefRemove ×
What’s different8.2K contextThe Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:”…Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions...
DateOct 16, 2026DiscoveredApr 17, 2025ListedOct 1, 2026Listed
Listed rate$0.02 in / $0.00 out/ 1M tokensExperiential · all routes ↗Standard list rateSee provider quotes$0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints1 endpoint →0 endpoints →2 endpoints →
Context window8.2K51265.5K
Max output——14.7K
Parameters———
Image inputNot reportedNot reportedSupported
Open weightsNot reportedNot reportedSupported

Add another model

Search all models →