DeepSeek V4 Pro Variant2
deepseek-v4-pro:variant2Pricing
List prices at EmpirioLabs AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.65 | $3.30 | |
| Cached input 92% off input | $0.138 | 92% off input | |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches |
What it costs a month
At EmpirioLabs AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$606
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$548
- Coding agent1,000 requests a day, 40K in / 2K out, cached$908
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,752
Where to run it
1 host serve DeepSeek V4 Pro Variant2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud deepseek-v4-pro:variant2 | $1.65 / $3.30 | deepseek-v4-pro:variant2 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt cachingBuilt-in web search
- Open weights
- License: DeepSeek License (MIT code)Runtimes: SGLang, TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than EmpirioLabs AI.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 3% less
- 27% less
- 39% less
- 90% less
Open-weight picks
- 16% less
- 58% less
- 62% less
- 67% less
Call it
Using EmpirioLabs AI's API.
from litellm import completion
response = completion(
model="empiriolabs/deepseek-v4-pro:variant2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4 Pro Variant2 cost?
On EmpirioLabs AI, DeepSeek V4 Pro Variant2 costs $1.65 per million input tokens and $3.30 per million output tokens. Cached input costs $0.138 per million tokens.
Which APIs offer DeepSeek V4 Pro Variant2?
DeepSeek V4 Pro Variant2 runs on 1 API: EmpirioLabs AI.
What is DeepSeek V4 Pro Variant2's context window?
1M tokens, with up to 393K tokens in one reply.
Is DeepSeek V4 Pro Variant2 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4 Pro Variant2?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (3% less), Gemini 3.8 Flash on Google AI Studio (27% less) and Inkling on DeepInfra (16% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4 Pro Variant2's API model id?
Use deepseek-v4-pro:variant2 with EmpirioLabs AI.
Sources
Raw catalog entry for deepseek-v4-pro:variant2 on EmpirioLabs AI
{
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"input_cost_per_token": 0.00000165,
"output_cost_per_token": 0.000003301,
"cache_read_input_token_cost": 1.38e-7,
"supports_system_messages": true,
"supports_reasoning": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01,
"search_context_size_high": 0.01
},
"supports_prompt_caching": true,
"supports_response_schema": true,
"source": "https://empiriolabs.ai/models/deepseek-v4-pro",
"supports_function_calling": true
}