Skip to main content

Voyage Multimodal 3 API pricing, benchmarks and specs | AshnaAI

Voyage AI

Voyage Multimodal 3

Previous-generation interleaved text and image embeddings for visual retrieval.

Try this model API docs

Model details

Model ID: voyage-multimodal-3
Provider: Voyage AI
Modality: Multimodal embedding
Context window: 32,000 tokens
Input → output: Text / image / video → vectors
Token rate limit: 2,000,000 TPM
Request rate limit: 2,000 RPM
Released: Nov 12, 2024

Available on AshnaAI

Oct 3, 2026

Where this model fits

Best capabilities

Shared text, image, and video vector representations
Visual-document and mixed-modality retrieval

Best for

Visual search
Slides, screenshots, figures, and video retrieval

Not ideal for

Conversational generation
Text-only embedding endpoints

Benchmarks

No comparable, source-verified benchmark has been published for this catalog entry yet.

Pricing (USD)

Limited-time 30% discount

Text input / 1M tokens: $0.145$0.101
Image or video / 1B pixels: $0.723$0.506

Capabilities

reasoning—
tools—
visionSupported
web search—
filesSupported

Available regions

US East (N. Virginia)

us-east-1

Europe (Frankfurt)

eu-central-1

Asia Pacific (Mumbai)

ap-south-1

Multi-region and provider failover: Active

Requests automatically switch to another region or provider if one becomes unavailable.