Rerank V3.5 API Pricing

As of October 10, 2026, Rerank V3.5 costs $2.00 per 1K queries on Cohere. It has a 4,096-token context window and returns up to 4,096 tokens per response.

By CohereModel ID rerank-v3.5Prices updated October 10, 2026Checked October 10, 2026

Input: $0 / 1M tokens
Output: $0 / 1M tokens
Context window: 4,096 tokens
Max output: 4,096 tokens
Providers: 2
Added to LiteLLM: December 2024

Rerank V3.5 pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Per 1K queries	Context
Cohere	`rerank-v3.5`	$0	$0	$2.00	4K
Amazon Bedrock	`cohere.rerank-v3-5:0`	$0	$0	$2.00	32K

Use Rerank V3.5 with LiteLLM

Call Rerank V3.5 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/rerank. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="rerank-v3.5",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: rerank-v3.5
    litellm_params:
      model: rerank-v3.5
      api_key: os.environ/COHERE_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "rerank-v3.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Rerank V3.5 FAQ

How much does Rerank V3.5 cost?

Rerank V3.5 costs $2.00 per 1K queries on Cohere.

What is the context window of Rerank V3.5?

Rerank V3.5 has a 4,096-token context window and returns up to 4,096 tokens per response.

Which providers offer Rerank V3.5?

Rerank V3.5 is available from 2 providers through LiteLLM: Cohere and Amazon Bedrock.

How do I call Rerank V3.5 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="rerank-v3.5", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/rerank from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Rerank V3.5?

Rerank V3.5 was added to LiteLLM's model price file in December 2024.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

LiteLLM docs: Cohere, Amazon Bedrock.

Provider pages: Cohere, Amazon Bedrock.