[Cohere](/ai-gateway/models/labs/cohere) # Cohere Rerank 4 Pro Cohere Rerank 4 Pro is a multilingual reranking model from Cohere built for state-of-the-art relevance on complex queries over English and non-English documents and semi-structured JSON. Your use is subject to Cohere's [Terms](https://cohere.com/terms-of-use) & [Privacy](https://cohere.com/privacy) Policies. Rerank [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) ``` 1import { rerank } from 'ai'; 2 3const result = await rerank({ 4 model: 'cohere/rerank-v4-pro', 5 query: 'What is the capital of France?', 6 documents: [ 7 'Paris is the capital of France.', 8 'Berlin is the capital of Germany.', 9 'Madrid is the capital of Spain.', 10 ], 11}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/rerank-v4-pro) [About](/ai-gateway/models/rerank-v4-pro/about) [Providers](/ai-gateway/models/rerank-v4-pro/providers) [Similar](/ai-gateway/models/rerank-v4-pro/similar) [FAQ](/ai-gateway/models/rerank-v4-pro/faq) ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Context | Input | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) [Cohere](/ai-gateway/models/providers/cohere) Legal:[Terms](https://cohere.com/terms-of-use)•[Privacy](https://cohere.com/privacy) | 32K | $2.50/K | | | | 12/11/2025 | | | --- | --- | --- | --- | --- | --- | --- | --- | ## [Copy link to heading](#more-models-by-cohere)More models by Cohere All Text Code Embed Rerank | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) [cohere/rerank\-v4-fast](/ai-gateway/models/rerank-v4-fast) | 32K | | | $2/K | | | — | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) | | | | 12/11/2025 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) [cohere/embed-v4.0](/ai-gateway/models/embed-v4.0) | 128K | | | $0.12/M | | | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) | | | | 04/15/2025 | | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) [cohere/command-a](/ai-gateway/models/command-a) | 256K | 0.2s | 49tps | $2.50/M | $10/M | | — | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) | | | | 03/13/2025 | | | ![cohere logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcohere.png&w=48&q=75) [cohere/rerank-v3.5](/ai-gateway/models/rerank-v3.5) | 4K | | | $2/K | | | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) | | | | 12/02/2024 | | ## [Copy link to heading](#about-cohere-rerank-4-pro)About Cohere Rerank 4 Pro Cohere Rerank 4 Pro is the quality tier of the Rerank 4 generation, released December 11, 2025 alongside `rerank-v4-fast`. Cohere positions it as the strongest Cohere reranker yet, aimed at enterprise search and RAG pipelines where ranking accuracy on complex queries directly drives downstream outcomes. Reranking is a cross-encoder step. Cohere Rerank 4 Pro reads the query and each candidate document together with full attention, scoring relevance in a way that bi-encoder embedding similarity cannot. Multi-part queries, queries with conditions, and queries that hinge on a single phrase inside a long document benefit most from this setup. Multilingual coverage spans more than 100 languages. A query in one language can match documents in another within the same rerank call, so a single index can serve a global user base without separate per-language pipelines. Document types include long-form text, tables, code, and semi-structured JSON. In a RAG pipeline, the common pattern is to retrieve 50 to 200 candidates with an embedding model, then rerank them with Cohere Rerank 4 Pro down to a top-k of 5 to 20 documents handed to the generative model. The reranker reduces noise in the LLM context, which often improves answer quality more than swapping in a larger generative model would. See https://cohere.com/blog/rerank-4 for the API contract. Reranking is billed per search query, so cost scales with traffic rather than document length or token count. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: Rerankers refine an existing candidate set; they don't replace retrieval. Pair Cohere Rerank 4 Pro with an embedding model, BM25, or hybrid retriever for the first pass. The per-document context of 32K tokens covers query and document tokens together, so very long documents may need chunking before they reach the model. - Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-cohere-rerank-4-pro)When to Use Cohere Rerank 4 Pro ### Best for - High-quality enterprise search: Top-k selection drives downstream outcomes in legal, financial, and support contexts - Complex query reasoning: Multi-part and conditional queries benefit from full cross-attention - Global multilingual RAG: One reranker covers more than 100 languages including cross-lingual matching - Long-document corpora: Chunked passages get precise final ordering before they hit the LLM context - Hybrid retrieval merging: BM25 and vector candidates share a single relevance score ### Consider alternatives when - Latency-critical pipelines: `rerank-v4-fast` is tuned for lower response time and higher throughput - English-only corpora: `rerank-v3.5` covers English RAG at a lower per-query price - First-pass alone is enough: The accuracy bar is met without a second stage - Multimodal retrieval: Pick a model with native image inputs ## [Copy link to heading](#conclusion)Conclusion Cohere Rerank 4 Pro is the right reranker when ranking accuracy on complex multilingual queries is what the application is judged on. Route it through AI Gateway with model id `cohere/rerank-v4-pro` to share billing and observability with the embedding and generative models in the same RAG pipeline.