LiteLLMModels

DeepSeek R1 Turbo API Pricing

As of October 10, 2026, DeepSeek R1 Turbo costs $0.70 per 1M input tokens and $2.50 per 1M output tokens from Novita AI, the lowest of 2 providers. It has a 64,000-token context window and returns up to 16,000 tokens per response.

By DeepSeekModel ID novita/deepseek/deepseek-r1-turboPrices updated Checked
Input
$0.70 / 1M tokens
Output
$2.50 / 1M tokens
Context window
64,000 tokens
Max output
16,000 tokens
Providers
2
Added to LiteLLM
August 2025

DeepSeek R1 Turbo 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
Novita AInovita/deepseek/deepseek-r1-turbo$0.70$2.5064K
DeepInfradeepinfra/deepseek-ai/DeepSeek-R1-Turbo$1.00$3.0040K

What DeepSeek R1 Turbo costs in practice

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

Novita AI$2.65
DeepInfra$3.50

DeepSeek R1 Turbo features

Use DeepSeek R1 Turbo with LiteLLM

Call DeepSeek R1 Turbo 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="novita/deepseek/deepseek-r1-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-r1-turbo
    litellm_params:
      model: novita/deepseek/deepseek-r1-turbo
      # 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-r1-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek R1 Turbo FAQ

How much does DeepSeek R1 Turbo cost?

DeepSeek R1 Turbo costs $0.70 per 1M input tokens and $2.50 per 1M output tokens from Novita AI, the lowest of 2 providers.

What is the context window of DeepSeek R1 Turbo?

DeepSeek R1 Turbo has a 64,000-token context window and returns up to 16,000 tokens per response.

Which providers offer DeepSeek R1 Turbo?

DeepSeek R1 Turbo is available from 2 providers through LiteLLM: Novita AI and DeepInfra. The lowest price is on Novita AI.

How do I call DeepSeek R1 Turbo with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/deepseek/deepseek-r1-turbo", 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 R1 Turbo support?

DeepSeek R1 Turbo supports function calling, parallel tool calls, structured output and reasoning.

When did LiteLLM add DeepSeek R1 Turbo?

DeepSeek R1 Turbo was added to LiteLLM's model price file in August 2025.

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: DeepInfra.

Provider pages: Novita AI, DeepInfra.