LiteLLMModels

DeepSeek Coder API Pricing

As of October 10, 2026, DeepSeek Coder costs $0.14 per 1M input tokens and $0.28 per 1M output tokens on DeepSeek, with cache reads at $0.014 per 1M tokens. It has a 128,000-token context window and returns up to 4,096 tokens per response.

By DeepSeekModel ID deepseek/deepseek-coderPrices updated Checked
Input
$0.14 / 1M tokens
Output
$0.28 / 1M tokens
Cache read
$0.014 / 1M tokens
Context window
128,000 tokens
Max output
4,096 tokens
Providers
1
Added to LiteLLM
May 2024

DeepSeek Coder 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
DeepSeekdeepseek/deepseek-coder$0.14$0.28$0.014128K

What DeepSeek Coder costs in practice

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

DeepSeek$0.42

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

DeepSeek$1.456

DeepSeek Coder features

Use DeepSeek Coder with LiteLLM

Call DeepSeek Coder 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/deepseek-coder",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-coder
    litellm_params:
      model: deepseek/deepseek-coder
      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-coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek Coder FAQ

How much does DeepSeek Coder cost?

DeepSeek Coder costs $0.14 per 1M input tokens and $0.28 per 1M output tokens on DeepSeek, with cache reads at $0.014 per 1M tokens.

What is the context window of DeepSeek Coder?

DeepSeek Coder has a 128,000-token context window and returns up to 4,096 tokens per response.

Which providers offer DeepSeek Coder?

DeepSeek Coder is available from DeepSeek through LiteLLM, using the model name deepseek/deepseek-coder.

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

Use the LiteLLM Python SDK with model="deepseek/deepseek-coder", 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 Coder support?

DeepSeek Coder supports function calling and prompt caching.

When did LiteLLM add DeepSeek Coder?

DeepSeek Coder was added to LiteLLM's model price file in May 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: DeepSeek.

Provider pages: DeepSeek.