LiteLLMModels

Cohere Embed V5 Fast API Pricing

As of October 10, 2026, Cohere Embed V5 Fast costs $0.08 per 1M input tokens on Azure AI Foundry. It has a 128,000-token context window.

Model ID azure_ai/Cohere-Embed-V5-FastPrices updated Checked
Scheduled for deprecation: Azure AI Foundry lists January 23, 2027 as the deprecation date for azure_ai/Cohere-Embed-V5-Fast.
Input
$0.08 / 1M tokens
Output
$0 / 1M tokens
Context window
128,000 tokens
Providers
1
Added to LiteLLM
October 10, 2026

Cohere Embed V5 Fast pricing by provider

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

ProviderModel name in LiteLLMInputOutputContext
Azure AI Foundryazure_ai/Cohere-Embed-V5-Fast$0.08$0128K

What Cohere Embed V5 Fast costs in practice

Embedding 10,000 documents of 500 tokens each

Azure AI Foundry$0.40

Cohere Embed V5 Fast features

Input: text, image.

Use Cohere Embed V5 Fast with LiteLLM

Call Cohere Embed V5 Fast through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/embeddings. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import embedding

response = embedding(
    model="azure_ai/Cohere-Embed-V5-Fast",
    input=["hello world"],
)
Proxy config.yaml
model_list:
  - model_name: cohere-embed-v5-fast
    litellm_params:
      model: azure_ai/Cohere-Embed-V5-Fast
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "cohere-embed-v5-fast",
    "input": "hello world"
  }'

Cohere Embed V5 Fast FAQ

How much does Cohere Embed V5 Fast cost?

Cohere Embed V5 Fast costs $0.08 per 1M input tokens on Azure AI Foundry.

What is the context window of Cohere Embed V5 Fast?

Cohere Embed V5 Fast has a 128,000-token context window.

Which providers offer Cohere Embed V5 Fast?

Cohere Embed V5 Fast is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/Cohere-Embed-V5-Fast.

How do I call Cohere Embed V5 Fast with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/Cohere-Embed-V5-Fast", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Cohere Embed V5 Fast?

Cohere Embed V5 Fast was added to LiteLLM's model price file on October 10, 2026.

Is Cohere Embed V5 Fast being deprecated?

Azure AI Foundry lists a deprecation date of January 23, 2027 for azure_ai/Cohere-Embed-V5-Fast.

Sources

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

LiteLLM docs: Azure AI Foundry.

Provider pages: Azure AI Foundry.