DeepSeek V4 Pro API Pricing
As of October 10, 2026, DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens on DeepSeek, with cache reads at $0.044 and cache writes at $0 per 1M tokens. Across 17 providers on LiteLLM, the input price ranges from $0.435 to $2.40. It has a 1,000,000-token context window and returns up to 393,216 tokens per response.
- Input
- $1.32 / 1M tokens
- Output
- $3.96 / 1M tokens
- Cache read
- $0.044 / 1M tokens
- Context window
- 1,000,000 tokens
- Max output
- 393,216 tokens
- Providers
- 17
- Added to LiteLLM
- June 2026
DeepSeek V4 Pro pricing by provider
25 listings across 17 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|---|
| DeepSeek | deepseek-v4-pro | $1.32 | $3.96 | $0.044 | $0 | 1M |
| DeepSeek | deepseek/deepseek-v4-pro | $1.32 | $3.96 | $0.044 | $0 | 1M |
| AIHubMix | aihubmix/deepseek-v4-pro | $1.69 | $3.38 | $0.1403 | – | 1M |
| Alibaba Cloud Model Studio | dashscope/deepseek-v4-pro | $2.40 | $4.80 | $0.20 | – | 1M |
| Azure AI Foundry | azure_ai/deepseek-v4-pro | $1.74 | $3.48 | $0.145 | – | 1M |
| Baseten | baseten/deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | $0.145 | – | 1M |
| Basetensnapshot 0813 | baseten/deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.132 | – | 1M |
| Databrickssnapshot 0813 | databricks/databricks-deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.132 | $1.32 | 1M |
| DeepInfra | deepinfra/deepseek-ai/DeepSeek-V4-Pro | $1.30 | $2.60 | $0.10 | – | 1M |
| DeepInfrasnapshot 0813 | deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813 | $1.30 | $2.60 | $0.10 | – | 1M |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/deepseek-v4-pro | $1.20 | $1.20 | $0.60 | – | 1M |
| Fireworks AIsnapshot 0813 | fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | – | 1M |
| Fireworks AIsnapshot 0813 | fireworks_ai/deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | – | 1M |
| Nebius AI Studio | nebius/deepseek-ai/DeepSeek-V4-Pro | $1.75 | $3.50 | – | – | 1M |
| Nebius AI Studiosnapshot 0813 | nebius/deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | – | – | 979K |
| Novita AI | novita/deepseek/deepseek-v4-pro | $1.60 | $3.20 | $0.135 | – | 1M |
| Novita AIsnapshot 0813 | novita/deepseek/deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.132 | – | 1M |
| Perplexitysnapshot 0813 | perplexity/perplexity/deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | – | – |
| Qianwen AI Platform | qwen_ai_platform/deepseek-v4-pro | $2.40 | $4.80 | $0.20 | – | 1M |
| QwenCloud | qwencloud/deepseek-v4-pro | $2.40 | $4.80 | $0.20 | – | 1M |
| Sailsnapshot 0813 | sail/deepseek-ai/DeepSeek-V4-Pro-0813 | $0.92 | $2.77 | $0.04 | – | 1M |
| Tencent TokenHub | tencent/deepseek-v4-pro | $0.435 | $0.87 | $0.003625 | $0 | 1M |
| Together AIsnapshot 0813 | together_ai/deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.13 | – | 1M |
| Weights & Biases | wandb/deepseek-ai/DeepSeek-V4-Pro | $1.15 | $2.55 | $0.20 | – | 1M |
| Weights & Biasessnapshot 0813 | wandb/deepseek-ai/DeepSeek-V4-Pro-0813 | $1.31 | $3.96 | $0.044 | – | 1M |
What DeepSeek V4 Pro costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| DeepSeek | $4.62 |
| Tencent TokenHub | $1.305 |
| Sail | $3.225 |
| Weights & Biases | $3.575 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| DeepSeek | $13.99 |
| Tencent TokenHub | $4.524 |
| Sail | $9.754 |
| Weights & Biases | $12.01 |
DeepSeek V4 Pro features
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Reasoning
- Prompt caching
Use DeepSeek V4 Pro with LiteLLM
Call DeepSeek V4 Pro 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.
from litellm import completion
response = completion(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: deepseek-v4-pro
litellm_params:
model: deepseek-v4-pro
api_key: os.environ/DEEPSEEK_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'DeepSeek V4 Pro FAQ
How much does DeepSeek V4 Pro cost?
DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens on DeepSeek, with cache reads at $0.044 and cache writes at $0 per 1M tokens. Across 17 providers on LiteLLM, the input price ranges from $0.435 to $2.40.
What is the context window of DeepSeek V4 Pro?
DeepSeek V4 Pro has a 1,000,000-token context window and returns up to 393,216 tokens per response.
Which providers offer DeepSeek V4 Pro?
DeepSeek V4 Pro is available from 17 providers through LiteLLM: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Perplexity and Qianwen AI Platform and 5 more. The lowest price is on Tencent TokenHub.
How do I call DeepSeek V4 Pro with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="deepseek-v4-pro", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does DeepSeek V4 Pro support?
DeepSeek V4 Pro supports function calling, parallel tool calls, structured output, reasoning and prompt caching. It does not support image input.
When did LiteLLM add DeepSeek V4 Pro?
DeepSeek V4 Pro was added to LiteLLM's model price file in June 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- api-docs.deepseek.com/quick_start/pricing
- aihubmix.com/api/v1/models
- www.alibabacloud.com/help/en/model-studio/models
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks.
Provider pages: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Perplexity, Qianwen AI Platform.
