Announcement

Cohere has released Embed v4, their latest embedding model that achieves significant improvements in accuracy, efficiency, and multilingual performance.

Key Improvements

Performance Gains

MTEB (Massive Text Embedding Benchmark) scores:

| Model | Dimensions | Avg Score | Retrieval | Classification | |-------|-----------|-----------|-----------|----------------| | Embed v3 | 1024 | 64.2 | 52.3 | 71.8 | | Embed v4 | 768 | 66.8 | 55.1 | 74.2 | | OpenAI ada-002 | 1536 | 60.9 | 49.2 | 68.5 | | OpenAI text-3-large | 3072 | 64.6 | 54.6 | 70.1 |

Reduced Dimensions

Moving from 1024 to 768 dimensions provides: • 25% less storage per embedding • 20% faster similarity search • 15% lower API costs • No accuracy loss (actually improved)

Multilingual Excellence

Embed v4 supports 100+ languages with strong performance: • English: 68.2 (MTEB) • Chinese: 65.1 • Spanish: 64.8 • Arabic: 62.3 • Hindi: 61.7

Cross-lingual retrieval (query in one language, retrieve in another) improved by 35%.

Technical Innovations

Matryoshka Embeddings

Embed v4 uses Matryoshka Representation Learning, allowing flexible dimension reduction:

``python Generate full 768-dim embedding full_embedding = co.embed(texts=["sample text"], model="embed-v4")

Truncate to smaller dimensions without recomputing embedding_256 = full_embedding[:256] Use first 256 dims embedding_512 = full_embedding[:512] Use first 512 dims

Trade-off: smaller size vs. slight accuracy loss `

Dimension vs. accuracy: • 768 dims: 100% accuracy (baseline) • 512 dims: 98.5% accuracy • 256 dims: 95.2% accuracy • 128 dims: 89.1% accuracy

Instruction-Aware Embeddings

Embed v4 takes optional task instructions for better domain adaptation:

`python Standard embedding embedding = co.embed( texts=["Machine learning model"], model="embed-v4" )

With task instruction for better domain alignment embedding = co.embed( texts=["Machine learning model"], model="embed-v4", input_type="search_document", embedding_types=["float"] )

For queries (different from documents) query_embedding = co.embed( texts=["How does ML work?"], model="embed-v4", input_type="search_query" ) `

Training Improvements

Trained on: • 1.2 trillion tokens (3x more than v3) • Synthetic hard negatives • Contrastive learning with dynamic batching • Multi-task training across 50+ tasks

Pricing

Embed v4 pricing (per 1M tokens): • embed-v4: $0.10 • embed-v4-light: $0.02 (384 dims, slightly lower accuracy)

Compared to competitors: • OpenAI text-embedding-3-small: $0.02 (1536 dims) • OpenAI text-embedding-3-large: $0.13 (3072 dims)

Migration Guide

Upgrading from v3 to v4:

`python Old (v3) response = co.embed( texts=texts, model="embed-english-v3.0" )

New (v4) response = co.embed( texts=texts, model="embed-v4", input_type="search_document" New parameter ) `

Note: v3 and v4 embeddings are not compatible. You must re-embed your entire corpus.

Use Cases

Embed v4 particularly excels at: • Multilingual search: Better cross-language retrieval • Code search: Improved semantic code understanding • Domain-specific RAG: Instruction parameter helps adaptation • Large-scale systems: Reduced dimensions = lower costs

Benchmarks

Retrieval Tasks

Tested on BeIR benchmark (zero-shot retrieval):

| Dataset | Embed v3 | Embed v4 | Improvement | |---------|----------|----------|-------------| | NQ | 52.8 | 56.3 | +6.6% | | HotpotQA | 63.2 | 67.1 | +6.2% | | FEVER | 75.3 | 79.8 | +6.0% | | Climate-FEVER | 23.1 | 28.4 | +22.9% | | SciFact | 66.2 | 71.8 | +8.5% |

Classification

On standard text classification benchmarks: • Banking77: 86.2% → 89.1% (+3.4%) • Amazon Reviews: 63.8% → 67.2% (+5.3%) • TREC: 91.3% → 93.7% (+2.6%)

Availability • Generally available via Cohere API • Supported in all SDKs (Python, Node.js, Go, Java) • Coming soon to AWS Bedrock and Azure • Self-hosted option via Cohere Private Deployment

Best Practices

Dimension Selection • 768 dims: Default, best quality • 512 dims: Good balance for most use cases • 256 dims: Cost-optimized, still strong performance

Input Types • search_document: For documents being indexed • search_query: For search queries • classification: For classification tasks • clustering`: For clustering tasks

Migration Strategy Test v4 on sample queries Compare retrieval quality Re-embed corpus incrementally Use A/B testing during transition

Conclusion

Embed v4 sets a new standard for production embedding models, combining state-of-the-art accuracy with practical efficiency improvements. The flexible dimensions via Matryoshka embeddings make it suitable for a wide range of deployment scenarios and budgets.