Side by side

See the difference.

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

Scroll to compare models →

Comparison of command-a, Topaz Upscale Image Generative, Moondream: Moondream 3 Preview
3 modelsUnknowncommand-aRemove ×topazTopaz Upscale Image GenerativeRemove ×moondreamMoondream: Moondream 3 PreviewRemove ×
What’s different256K context · 8.2K max output · Tool calling · Structured outputProfessional generative image upscaling powered by Topaz Labs. Wonder 3.5 leads the range, with Redefine for prompt-guided detail and Recovery for extreme low-resolution sources. Best for rebuilding sharp…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…
DateOct 16, 2026DiscoveredAug 11, 2026ListedOct 15, 2026Listed
Listed rate$2.50 in / $10.00 out/ 1M tokensExperiential · all routes ↗Standard list rateSee provider quotes$0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8
Provider endpoints1 endpoint →0 endpoints →2 endpoints →
Context window256K—32K
Max output8.2K—4.1K
Parameters———
Tool callingSupportedNot reportedNot reported
Structured outputSupportedNot reportedNot reported
Image inputNot reportedNot reportedSupported
ReasoningNot reportedNot reportedSupported
Open weightsNot reportedNot reportedSupported

Add another model

Search all models →