cohere
Cohere: Rerank 4 Pro
cohere/rerank-4-pro
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to OpenRouter's catalog entry, cohere/rerank-4-pro is a Cohere reranking model intended to improve the relevance of results in search and retrieval-augmented generation systems. The catalog reports a 32K-token context window, text input with rerank output, multilingual coverage across more than 100 languages, and no data pre-processing requirement. No benchmark measurements or independent model card were included in this source pack, so these capabilities are source-reported rather than independently verified.[1]
Strengths
- OpenRouter's catalog describes it as an AI search foundation model for improving relevance in search and RAG systems.[1]
- The catalog reports a 32K context window and multilingual support across more than 100 languages.[1]
- Its text-to-rerank modality is explicitly suited to ordering text candidates rather than generating responses.[1]
Limitations
- Only OpenRouter catalog evidence was supplied, and no independent model card was available in this source pack.[1]
- The catalog entry contains no benchmark results, so measured quality, latency, and workload fit remain unverified.[1]
- Supported parameters, knowledge cutoff, and reasoning capability are empty or null in the catalog data, so they should be treated as unknown rather than confirmed absent.[1]
Where to use it
- Editorial suggestion: consider for reranking retrieved passages in RAG pipelines, after validating relevance on your own data.[1]
- Potentially useful for multilingual search result ordering, subject to testing the specific languages and domains.[1]
- May fit search stacks that need to evaluate long candidate sets within the reported 32K context window.[1]
Sources
- [1] OpenRouter catalog · Cohere: Rerank 4 ProSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...
Specifications
- Model ID
- cohere/rerank-4-pro
- Creator
- cohere
- Added to OpenRouter
- 06.04.2026
- Context length
- 32,768
- Modality
- text->rerank
- Input modalities
- text
- Output modalities
- rerank
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- 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 | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
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 | 32,768 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.