AI TOOLS RADAR
Esplora
Tutti i modelli / COHERE
cohere logo
cohere

Cohere: Rerank 4 Pro

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Priced at $0.0025 per search. 32,768 token context window.

Vedi la fonte su OpenRouter
Panoramica

Specifiche del modello

Contesto
32.768 tokens
Output massimo
29.491 tokens
Architettura
text->rerank
Tokenizer
Cohere
Limite di conoscenza
Non indicato
Moderato
Sì
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Search units
$0.0025
/search
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"cohere/rerank-4-pro","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
text
Output
rerank
API

Parametri API supportati

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
Provider disponibili

1 Provider

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

Cohere

unknown
Contesto
33K
Output massimo
29K
Input
Gratuito
Output
Gratuito
Lettura cache
Non indicato
Scrittura cache
Non indicato
cohere

modelli

Tutti i modelli
cohere logocohere

Cohere: North Mini Code (free)

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...

Contesto
256K
Input
text
Output
text
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →
cohere logocohere

Cohere: Rerank 4 Fast

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...

Contesto
33K
Input
text
Output
rerank
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →
cohere logocohere

Cohere: Rerank v3.5

Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search...

Contesto
4K
Input
text
Output
rerank
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →
cohere logocohere

Cohere: Command A

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

Contesto
256K
Input
text
Output
text
Input: $2.50Output: $10.00per milione di token
Vedi i dettagli del modello →