impulse

Rerank V4.0 Pro

Rerank
API id rerank-v4.0-pro
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Rerank V4.0 Pro. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
CohereLab API
rerank-v4.0-pro
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Cohere models

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

Model line

Newer and older versions, at each lab's own price.

  1. UndatedRerank V5.0 ProLatest$0.05 / $0.00
  2. UndatedRerank V4.0 ProThis pageNot listed

Call it

Using Cohere's API.

Python
from litellm import completion

response = completion(
    model="cohere/rerank-v4.0-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Rerank V4.0 Pro?

Rerank V4.0 Pro runs on 1 API: Cohere.

What is Rerank V4.0 Pro's context window?

33K tokens, with up to 33K tokens in one reply.

Is Rerank V4.0 Pro being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Rerank V4.0 Pro?

Yes. Rerank V5.0 Pro is the newest model in this line.

What is Rerank V4.0 Pro's API model id?

Use rerank-v4.0-pro with Cohere.

Sources

Raw catalog entry for rerank-v4.0-pro on Cohere
{
  "input_cost_per_query": 0.0025,
  "input_cost_per_token": 0,
  "litellm_provider": "cohere",
  "max_input_tokens": 32768,
  "max_output_tokens": 32768,
  "mode": "rerank",
  "output_cost_per_token": 0,
  "source": "https://cohere.com/pricing"
}