Primary use stated or inferred cautiously from official documentation.
C
COHERE / embed-v4.0
Cohere Embed 4
Multimodal embedding model for text, images, and mixed documents with configurable dimensions.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | embed-v4.0 |
|---|---|
| Model type | Embeddings · Vision and documents |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · PDF |
| Exit | Vector |
| Context window | 128,000 tokens |
| maximum output | 256, 512, 1,024 or 1,536 dimensions |
| Reasoning | Not applicable or not published |
| Published tools | |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Cohere API · Nube privada |
Enterprise RAG, visual document search, and multilingual retrieval.
Measure recall with your documents and the impact of dimensionality, storage, and reindexing.
03 / CAPABILITIES
What it can do
Orientation
Enterprise RAG, visual document search, and multilingual retrieval.
Context
128,000 tokens · 256, 512, 1,024 or 1,536 dimensions
Tools and integration
Not published
Access
Cohere API and private deployment
Input modalities
TextImagePDF
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Evaluaciones Embed 4 | Published | Multimodal retrieval | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Cohere Embed 4
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
Cohere Embed 4: How to Migrate a Multimodal Index Without Mixing Vector Spaces
Embed 4 can generate representations for text, images, and mixed inputs. But adding it to an existing index requires recalculating and validating vectors, queries, and configuration. Its specifications alone do not show that retrieval will improve on a particular corpus.
25 Sep 2026 ↗
Claude Sonnet 5 and Cohere Embed 4 in Multimodal RAG: How to Separate a Retrieval Failure from a Response Failure
Claude Sonnet 5 and Cohere Embed 4 occupy different layers in a multimodal RAG system. This guide proposes a factorial experiment, with a frozen corpus and conditions, to measure separately whether the right evidence was retrieved and whether the response used it faithfully.
22 Sep 2026 ↗07 / SOURCES