cohere
Cohere: Embed 5 Pro
cohere/embed-5-pro
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, cohere/embed-5-pro is Cohere's higher-accuracy tier in the Embed 5 family of multimodal embedding models. The catalog reports roughly 2.4 billion parameters and says it turns text, images, and interleaved text-image content into embeddings, with a long context window. Its output is embeddings rather than generated text, and the catalog does not identify a reasoning mode. These are source-reported capabilities: no independent model card or benchmark result was available in this pack, so workload testing remains necessary.[1]
Strengths
- The catalog reports a single model that accepts text, images, and interleaved text-image input and produces embeddings.[1]
- OpenRouter presents this exact variant as the higher-accuracy tier of Cohere's Embed 5 family; that is a catalog claim, not a measured benchmark result.[1]
- An advertised long context window may help with lengthy inputs or richer combined content, pending task-specific validation.[1]
Limitations
- Evidence is catalog-only: the source pack does not include an independent Cohere model card, so technical detail beyond OpenRouter's listing is limited.[1]
- No benchmark entries are supplied, leaving comparative accuracy, latency, robustness, and multilingual performance unverified.[1]
- The listing contains no supported request parameters and omits license terms, hardware or deployment requirements, and safety details; these gaps should not be read as confirmed absences.[1]
Where to use it
- Possible fit for multimodal semantic search or retrieval-augmented generation when an application needs embeddings for text, image, or mixed items, subject to evaluation.[1]
- Could be considered for clustering, classification, recommendation, or duplicate-detection pipelines that consume embeddings rather than generated text.[1]
- May suit teams evaluating a Cohere embedding endpoint through OpenRouter, provided they validate quality, operational behavior, and total cost on their own data.[1]
Sources
- [1] OpenRouter catalog · Cohere: Embed 5 ProSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into...
Specifications
- Model ID
- cohere/embed-5-pro
- Canonical ID
- cohere/embed-5-pro-20261029
- Creator
- cohere
- Added to OpenRouter
- 03.11.2026
- Context length
- 128,000
- Modality
- text+image->embeddings
- Input modalities
- text, image
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.120 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Cohere | 128,000 | $0.120 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.