LiteLLMModels

Fw DeepSeek V4 Pro API Pricing

As of October 10, 2026, Fw DeepSeek V4 Pro costs $1.925 per 1M input tokens and $3.828 per 1M output tokens on Azure AI Foundry, with cache reads at $0.165 per 1M tokens. It has a 1,000,000-token context window and returns up to 384,000 tokens per response.

Model ID azure_ai/FW-DeepSeek-V4-ProPrices updated Checked
Input
$1.925 / 1M tokens
Output
$3.828 / 1M tokens
Cache read
$0.165 / 1M tokens
Context window
1,000,000 tokens
Max output
384,000 tokens
Providers
1
Added to LiteLLM
August 14, 2026

Fw DeepSeek V4 Pro 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 LiteLLMInputOutputCache readContext
Azure AI Foundryazure_ai/FW-DeepSeek-V4-Pro$1.925$3.828$0.1651M

What Fw DeepSeek V4 Pro costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Azure AI Foundry$5.764

100 long-document requests with 100,000 input and 2,000 output tokens each

Azure AI Foundry$20.02

Fw DeepSeek V4 Pro features

Use Fw DeepSeek V4 Pro with LiteLLM

Call Fw DeepSeek V4 Pro through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="azure_ai/FW-DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: fw-deepseek-v4-pro
    litellm_params:
      model: azure_ai/FW-DeepSeek-V4-Pro
      # credentials: see the provider's LiteLLM docs page
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": "fw-deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Fw DeepSeek V4 Pro FAQ

How much does Fw DeepSeek V4 Pro cost?

Fw DeepSeek V4 Pro costs $1.925 per 1M input tokens and $3.828 per 1M output tokens on Azure AI Foundry, with cache reads at $0.165 per 1M tokens.

What is the context window of Fw DeepSeek V4 Pro?

Fw DeepSeek V4 Pro has a 1,000,000-token context window and returns up to 384,000 tokens per response.

Which providers offer Fw DeepSeek V4 Pro?

Fw DeepSeek V4 Pro is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/FW-DeepSeek-V4-Pro.

How do I call Fw DeepSeek V4 Pro with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/FW-DeepSeek-V4-Pro", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Fw DeepSeek V4 Pro support?

Fw DeepSeek V4 Pro supports function calling, reasoning and prompt caching.

When did LiteLLM add Fw DeepSeek V4 Pro?

Fw DeepSeek V4 Pro was added to LiteLLM's model price file on August 14, 2026.

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.