LiteLLMModels

DeepSeek Prover V2 671B API Pricing

As of October 10, 2026, DeepSeek Prover V2 671B costs $0.70 per 1M input tokens and $2.50 per 1M output tokens on Novita AI. It has a 160,000-token context window and returns up to 160,000 tokens per response.

By DeepSeekModel ID novita/deepseek/deepseek-prover-v2-671bPrices updated Checked
Input
$0.70 / 1M tokens
Output
$2.50 / 1M tokens
Context window
160,000 tokens
Max output
160,000 tokens
Providers
1
Added to LiteLLM
August 2025

DeepSeek Prover V2 671B 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 LiteLLMInputOutputContext
Novita AInovita/deepseek/deepseek-prover-v2-671b$0.70$2.50160K

What DeepSeek Prover V2 671B costs in practice

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

Novita AI$2.65

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

Novita AI$7.50

Use DeepSeek Prover V2 671B with LiteLLM

Call DeepSeek Prover V2 671B 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-prover-v2-671b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-prover-v2-671b
    litellm_params:
      model: novita/deepseek/deepseek-prover-v2-671b
      # 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-prover-v2-671b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek Prover V2 671B FAQ

How much does DeepSeek Prover V2 671B cost?

DeepSeek Prover V2 671B costs $0.70 per 1M input tokens and $2.50 per 1M output tokens on Novita AI.

What is the context window of DeepSeek Prover V2 671B?

DeepSeek Prover V2 671B has a 160,000-token context window and returns up to 160,000 tokens per response.

Which providers offer DeepSeek Prover V2 671B?

DeepSeek Prover V2 671B is available from Novita AI through LiteLLM, using the model name novita/deepseek/deepseek-prover-v2-671b.

How do I call DeepSeek Prover V2 671B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/deepseek/deepseek-prover-v2-671b", 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.

When did LiteLLM add DeepSeek Prover V2 671B?

DeepSeek Prover V2 671B 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.

Provider pages: Novita AI.