Cohere
Models published by Cohere, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
Command A+ is Cohere's first Mixture-of-Experts model, combining vision input support, reasoning, agentic tool use, and world-class translation in a single set of weights. With 25B active parameters, it targets complex multimodal agentic tasks and balances accuracy with efficiency, supporting 48 languages. It offers a 128K-token context window with up to 64K tokens of output and is released open-weight.
Command A is Cohere's performant flagship model for agentic, multilingual, and enterprise use cases. It is optimized for tool use, retrieval-augmented generation, and complex reasoning, supports 23 languages, and offers a 256K-token context window with strong throughput on minimal hardware. Released open-weight for research use.
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent. It offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.
Cohere's Rerank Multilingual 3.0 scores how relevant each document is to a query, for non-English and mixed-language search. Use it as a second stage after vector or keyword search.
Cohere's Rerank 3.5 scores how relevant each document is to a query. It handles 100+ languages and long, semi-structured documents (emails, tables, JSON, code). Use it as a second stage after vector or keyword search to put the best passages first.
Cohere's Rerank 4.0 Fast is the low-latency Rerank 4 variant. It scores how relevant each document is to a query across 100+ languages. Use it as a second stage after vector or keyword search when latency matters more than the last bit of quality.
Cohere's Rerank 4.0 Pro is the highest-quality Cohere reranker. It scores how relevant each document is to a query across 100+ languages, with a longer context per document than Rerank 3.5. Use it as a second stage after vector or keyword search when ranking quality matters most.