Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | nvidiaNemotron-3.5-ASR-Streaming-Multilingual-0.6bRemove × | cloudflareCloudflare: Clef FlashRemove × |
|---|---|---|
| What’s different | Nemotron 3.5 ASR Streaming Multilingual is an open 0.6B-parameter prompt-conditioned cache-aware FastConformer-RNNT model, engineered for low-latency streaming transcription across 40+ languages. It powers… | Small decision model for routing and scoring; the Workers AI route currently reads only roughly the first 2K text-state tokens. |
| Date | Jun 3, 2026Listed | Oct 1, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $3.33 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.038 in / $0.00 out/ 1M tokensDeepInfra · all routes ↗ |
| Provider endpoints | 2 endpoints → | 2 endpoints → |
Specifications | ||
| Context window | — | 24.6K |
| Max output | — | 22.1K |
| Parameters | 0.6B | — |
| Image input | Not reported | Supported |
| Audio input | Supported | Not reported |
| Open weights | Supported | Supported |