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-large, Moondream: Moondream 3.1
2 modelsUnknowntext-embedding-3-largeRemove ×moondreamMoondream: Moondream 3.1Remove ×
What’s different8.2K contextNative object detection and pointing return structured coordinates; runs locally on Apple Silicon or NVIDIA GPUs.
DateOct 16, 2026DiscoveredOct 15, 2026Listed
Listed rate$0.13 in / $0.00 out/ 1M tokensExperiential · all routes ↗Standard list rate$0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8
Provider endpoints1 endpoint →2 endpoints →
Context window8.2K32K
Max output—4.1K
Parameters—9B
Image inputNot reportedSupported
ReasoningNot reportedSupported
Open weightsNot reportedSupported

Add another model

Search all models →