ZMIME

Dhīr 5B MoE vs Ripple-65B Preview vs EKA-1

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationDhīr 5B MoEZenteiQRipple-65B PreviewRicursive IntelligenceEKA-1Soket AI
TaskMultilingual assistantLanguage generation and codingMultilingual reasoning and coding
Published capabilitiesMixture-of-experts assistant supporting English and ten Indian languages for offline deployment.Dense transformer trained on 12 trillion tokens with a focus on long-context software engineering.Trained on about 7.5 trillion tokens across English and all 22 scheduled Indian languages.
Model size5.09B total / 1.79B active65B parameters26.3B parameters
AccessOpen weights for on-premises or offline usePublic weights and hosted inference via Together AI, OpenRouter and FireworksReleased through the IndiaAI Mission
SourcesPublisher documentation · Additional documentationPublisher documentation · Model weightsPublisher documentation
InputsTextTextText
Context window16,384 tokens1,048,576 tokens—
Input price per million tokens———
Output price per million tokens———
WeightsOpen weightsOpen weightsWeights unconfirmed
ReleasedNov 3, 2026Nov 4, 2026Nov 3, 2026