Cohere's Rerank 3.5 is a 131K token text model ideal for chat and embedding tasks, with no credit card required and openAI incompatible, offering 10 RPM rate limit.
https://api.cohere.com/v2 rerank-3-5 Rerank 3.5 is listed for chat, embedding workloads and supports a 131K context window.
Check Cohere's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this Rerank 3.5 listing on Cohere in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Rerank 3.5 | Check provider | 131K | Native | 10 RPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| Command A+ (218B) | Cohere | 436K | Free tier |
| Command A (111B) | Cohere | 288K | Free tier |
| Command R+ | Cohere | 128K | Free tier |
| Command R7B | Cohere | 128K | Free tier |
| Command A Reasoning | Cohere | 288K | Free tier |
Rerank 3.5 is tagged for chat in this catalog.
Rerank 3.5 is tagged for embedding in this catalog.
Rerank 3.5 appears in the free model catalog for Cohere, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is rerank-3-5.
The listed free tier limit is 10 RPM. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 131K tokens with up to 131K output tokens.
Cohere's Rerank 3.5 is a 131K token text model ideal for chat and embedding tasks, with no credit card required and openAI incompatible, offering 10 RPM rate limit.
For API keys, setup steps, and provider-level limits, see the Cohere provider page.