Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | googleGoogle: Gemini 3.5 TranscribeRemove × | moondreamMoondream: Moondream 3 PreviewRemove × |
|---|---|---|
| What’s different | Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio... | Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over… |
| Date | Sep 25, 2026Listed | Oct 15, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $2.00 in / $12.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8 |
| Provider endpoints | 1 endpoint → | 2 endpoints → |
Specifications | ||
| Context window | 98.3K | 32K |
| Max output | 32.8K | 4.1K |
| Parameters | — | — |
| Image input | Not reported | Supported |
| Audio input | Supported | Not reported |
| Reasoning | Not reported | Supported |
| Open weights | Not reported | Supported |