LiteLLMModels

DeepSeek Coder V2 Lite Base API Pricing

As of October 10, 2026, DeepSeek Coder V2 Lite Base is free to use from Ollama, the lowest of 2 providers. It has an 8,192-token context window and returns up to 8,192 tokens per response.

By DeepSeekModel ID ollama/deepseek-coder-v2-lite-basePrices updated Checked
Price
Free
Context window
8,192 tokens
Max output
8,192 tokens
Providers
2
Added to LiteLLM
August 2024

DeepSeek Coder V2 Lite Base 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.

ProviderModel name in LiteLLMInputOutputContext
Ollamaollama/deepseek-coder-v2-lite-base$0$08K
Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base$0.50$0.50160K

What DeepSeek Coder V2 Lite Base costs in practice

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

Ollama$0
Fireworks AI$1.25

DeepSeek Coder V2 Lite Base features

Use DeepSeek Coder V2 Lite Base with LiteLLM

Call DeepSeek Coder V2 Lite Base through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="ollama/deepseek-coder-v2-lite-base",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-coder-v2-lite-base
    litellm_params:
      model: ollama/deepseek-coder-v2-lite-base
      # 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": "deepseek-coder-v2-lite-base",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek Coder V2 Lite Base FAQ

How much does DeepSeek Coder V2 Lite Base cost?

DeepSeek Coder V2 Lite Base is free to use from Ollama, the lowest of 2 providers.

What is the context window of DeepSeek Coder V2 Lite Base?

DeepSeek Coder V2 Lite Base has an 8,192-token context window and returns up to 8,192 tokens per response.

Which providers offer DeepSeek Coder V2 Lite Base?

DeepSeek Coder V2 Lite Base is available from 2 providers through LiteLLM: Ollama and Fireworks AI. The lowest price is on Ollama.

How do I call DeepSeek Coder V2 Lite Base with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="ollama/deepseek-coder-v2-lite-base", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does DeepSeek Coder V2 Lite Base support?

DeepSeek Coder V2 Lite Base supports function calling.

When did LiteLLM add DeepSeek Coder V2 Lite Base?

DeepSeek Coder V2 Lite Base was added to LiteLLM's model price file in August 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: Ollama, Fireworks AI.

Provider pages: Ollama, Fireworks AI.