LiteLLMModels

DeepSeek Reasoner API Pricing

As of October 10, 2026, DeepSeek Reasoner costs $0.28 per 1M input tokens and $0.42 per 1M output tokens on DeepSeek, with cache reads at $0.028 per 1M tokens. It has a 131,072-token context window and returns up to 65,536 tokens per response.

By DeepSeekModel ID deepseek-reasonerPrices updated Checked
Deprecated: DeepSeek lists July 24, 2026 as the deprecation date for deepseek-reasoner.
Input
$0.28 / 1M tokens
Output
$0.42 / 1M tokens
Cache read
$0.028 / 1M tokens
Context window
131,072 tokens
Max output
65,536 tokens
Providers
1
Added to LiteLLM
January 2025

DeepSeek Reasoner pricing by provider

2 listings 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
DeepSeekdeepseek-reasoner$0.28$0.42$0.028128K
DeepSeekdeepseek/deepseek-reasoner$0.28$0.42$0.028128K

What DeepSeek Reasoner costs in practice

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

DeepSeek$0.77

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

DeepSeek$2.884

DeepSeek Reasoner features

Use DeepSeek Reasoner with LiteLLM

Call DeepSeek Reasoner 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="deepseek-reasoner",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-reasoner
    litellm_params:
      model: deepseek-reasoner
      api_key: os.environ/DEEPSEEK_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": "deepseek-reasoner",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek Reasoner FAQ

How much does DeepSeek Reasoner cost?

DeepSeek Reasoner costs $0.28 per 1M input tokens and $0.42 per 1M output tokens on DeepSeek, with cache reads at $0.028 per 1M tokens.

What is the context window of DeepSeek Reasoner?

DeepSeek Reasoner has a 131,072-token context window and returns up to 65,536 tokens per response.

Which providers offer DeepSeek Reasoner?

DeepSeek Reasoner is available from DeepSeek through LiteLLM, using the model name deepseek-reasoner.

How do I call DeepSeek Reasoner with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepseek-reasoner", 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 DeepSeek Reasoner support?

DeepSeek Reasoner supports structured output, reasoning and prompt caching. It does not support function calling and parallel tool calls.

When did LiteLLM add DeepSeek Reasoner?

DeepSeek Reasoner was added to LiteLLM's model price file in January 2025.

Is DeepSeek Reasoner being deprecated?

DeepSeek deprecated deepseek-reasoner on July 24, 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: DeepSeek.

Provider pages: DeepSeek.