Cohere Embed V4

coherecohere/embed-v4

Multilingual multimodal embedding model capable of transforming images, texts, and interleaved content into vector representations. State-of-the-art performance with byte/binary quantization and matryoshka embeddings for compression.

Official model card ↗Release announcement ↗Cohere Blog ↗Amazon Bedrock availability ↗

Cohere Embed v4 (embed-v4.0) is Cohere's first production-grade multimodal embedding model, released April 15, 2025. It natively converts text, images, and interleaved documents (PDFs, presentations, financial reports) into a single unified vector space without requiring separate preprocessing pipelines. The model supports Matryoshka embeddings in four dimensions (256, 512, 1024, 1536 default) and a 128 k token context window — 256× longer than its V3 predecessor.

Embed v4 is fine-tuned for enterprise domains (finance, healthcare, manufacturing) and achieves state-of-the-art results on text-to-text, text-to-image, and text-to-mixed-modality retrieval. It supports over 100 languages for text and is available on the Cohere Platform, AWS Bedrock (since Oct 2025), SageMaker, Azure AI Foundry, and Oracle OCI. TheRouter exposes it under the stable slug cohere/embed-v4 with full OpenAI-compatible embeddings syntax.

Best for

• Multimodal RAG over business documents (PDFs, slides, scanned reports) that contain text + tables + diagrams without manual chunking or OCR preprocessing
• Cross-lingual semantic search across 100+ languages in a single index; ideal for global knowledge bases and customer-support archives
• Industry-specific retrieval (finance, healthcare, manufacturing) where domain-tuned embeddings outperform generic models on specialized terminology
• Cost-sensitive vector storage with Matryoshka dimensions — drop from 1536 → 256 to cut storage ~83% while retaining most retrieval quality

Reach for something else if

• Pure code or math retrieval — specialized code embedding models (e.g. Qwen text-embedding-v4 or OpenAI text-embedding-3-large) remain stronger on code semantics
• Real-time image-only search at scale — models trained exclusively on vision (CLIP, SigLIP) may offer higher throughput for image-only workloads
• On-premise or air-gapped deployments — Embed v4 is only available through managed cloud endpoints (Cohere, AWS, Azure, OCI)

Context Length

Max Output

Input Priceper 1M tokens

$0.1296/ 1M tokens

Modalities

textimage→embedding

Capabilities

Vision

Pricing Breakdown

Type	Rate
Input	$0.1296 / 1M tokens

Supported Parameters

input_typedimensionstruncate

Specifications

Release date	2025-04-15Cohere Blog ↗	verified
Output dimensions	256, 512, 1024, 1536 (default)docs.cohere.com ↗	verified
Context length	128,000 tokensdocs.cohere.com ↗	verified
Multimodal input	Text + image + interleaved (PDFs, slides)docs.cohere.com ↗	verified
Supported languages (text)	100+docs.cohere.com ↗	verified
Image input language	English onlydocs.oracle.com ↗	verified
Training cutoff	Not publicly disclosed	unknown
Matryoshka embeddings	Yes (4 dimensions)docs.cohere.com ↗	verified

Benchmarks

Benchmark	Distribution	Score	Source
MTEB (Massive Text Embedding Benchmark) Pure-text score; multimodal capability not captured by standard MTEB		65.2score	Ailog RAG benchmark summary ↗

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL

curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "cohere/embed-v4",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'

API guide

Embeddings request

Generate embeddings for text, image, or mixed inputs. TheRouter routes transparently to Cohere with full OpenAI-compatible syntax.

cURL

curl https://api.therouter.ai/v1/embeddings \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/embed-v4",
    "input": ["Your text or image URL here"],
    "dimensions": 1024,
    "encoding_format": "float"
  }'

More from cohere

cohere/command-aCohere's flagship text-generation model; pair with Embed v4 for retrieval-augmented generation pipelines.cohere/command-r-plusEnterprise-grade reasoning model; complements Embed v4 for complex post-retrieval synthesis.

Similar models

Cross-provider sibling models

amazon/titan-embed-v2

AWS-native text embedding with configurable dimensions (256-1024); lower max dimension than Embed v4 and text-only.

openai/text-embedding-3-large

OpenAI's strongest general-purpose embedding model; 3072 dimensions, text-only, strong multilingual coverage but no native image support.

qwen/text-embedding-v4

Alibaba's latest embedding model with strong code and math retrieval; text-only, 8K context.

Fact ledger — every claim on this page traces here

source	URL	retrieved
Release date	Cohere Blog ↗	2026-05-25	verified
Output dimensions	docs.cohere.com ↗	2026-05-25	verified
Context length	docs.cohere.com ↗	2026-05-25	verified
Multimodal input	docs.cohere.com ↗	2026-05-25	verified
Supported languages (text)	docs.cohere.com ↗	2026-05-25	verified
Image input language	docs.oracle.com ↗	2026-05-25	verified
Training cutoff	—	—	unknown
Matryoshka embeddings	docs.cohere.com ↗	2026-05-25	verified
MTEB (Massive Text Embedding Benchmark)	Ailog RAG benchmark summary ↗	2026-05-25	to verify