DeepSeek V4 Pro

deepseek/deepseek-v4-pro
FlagshipFeatured
by DeepSeek · 2026-04-24

DeepSeek V4 Pro: flagship model with 1M token context, 384K output, and 96.2 τ²-Bench score.

ctx1.05M tokens
Inputtext
p50 TTFT872 ms
INPUT$0.44/ 1M tokens
OUTPUT$0.88/ 1M tokens
p50 TTFT872 ms7d
p95 TTFT3.00 s7d
TRAFFIC1604.1Mtokens / 7d

Model details

What is DeepSeek V4 Pro?

DeepSeek V4 Pro is the flagship text-generation model offered by DeepSeek and available through OrcaRouter's API. It is designed for tasks that require processing very large amounts of token context—up to 1,048,576 tokens—and generating outputs of up to 384,000 tokens. The model is text-only, meaning it does not accept or produce images, audio, or other non-text modalities. Its pricing is transparent: $0.44 per 1 million input tokens and $0.87 per 1 million output tokens, with OrcaRouter passing the provider rate directly at zero markup. The model achieves a τ²-Bench score of 96.2, reflecting strong performance in agentic tool-use scenarios. It is accessed via an OpenAI-compatible API endpoint at https://api.orcarouter.ai/v1 using the model identifier 'deepseek/deepseek-v4-pro'.

Who is this model intended for?

DeepSeek V4 Pro targets developers, data scientists, and researchers who regularly work with very long contexts—such as legal documents, multi-file codebases, or extensive research papers. Its large output limit (384,000 tokens) also suits applications that require generating substantial structured content, like book-length drafts or comprehensive reports. Because of its high context capacity, it is especially valuable for multi-turn applications where the entire conversation history must remain in the model’s view. However, for short, single-turn queries or tasks with limited context, a smaller or cheaper model may be more cost-effective. This model is also suitable for benchmarking agentic performance thanks to its strong τ²-Bench score.

What are the key specifications?

Key specifications include a context window of 1,048,576 tokens and a maximum output of 384,000 tokens. The model operates on text input only. Pricing is set at $0.44 per 1 million input tokens and $0.87 per 1 million output tokens, with zero markup on the provider rate. The model’s headline benchmark score is 96.2 on τ²-Bench, a measure that evaluates a model’s ability to use tools in an agentic setting. It is hosted by OrcaRouter and can be called via the OpenAI-compatible API at https://api.orcarouter.ai/v1 with model ID 'deepseek/deepseek-v4-pro'. These specifications make it one of the highest-capacity text models in terms of context and output length available through OrcaRouter.

How does OrcaRouter provide access?

OrcaRouter offers DeepSeek V4 Pro through its OpenAI-compatible API. Users send requests to https://api.orcarouter.ai/v1 with the model parameter set to 'deepseek/deepseek-v4-pro'. The API supports standard chat completions endpoints and parameters (e.g., temperature, max_tokens, stop). OrcaRouter adds no markup to the provider’s pricing, so the billed rate matches the $0.44/$0.87 per million tokens. This setup simplifies migration for teams already using the OpenAI client library—they only need to change the base URL and model name. OrcaRouter handles routing and reliability without requiring any extra authentication beyond an API key.

Code samples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Pricing

Input / 1M tokens$0.442
Output / 1M tokens$0.884
Cache read / 1M$0.060
CurrencyUSD

Performance

p50 TTFT
872 ms
Output speed
63.1 tok/s
p95 TTFT
3.00 s
Error rate
0.46%

Public benchmarks

62.5
AA Coding
Better than 91% of models compared
67.5
AA Intelligence
Better than 94% of models compared
62.5
AA Math
Better than 49% of models compared
GPQA Diamond
56.5 index
Humanity's Last Exam
35.9
IFBench
76.5
Long-Context Recall
66.3
MMLU-Pro
73.5 index
SciCode
50.0
TerminalBench Hard
46.2
τ²-Bench
54.5 index
Source: artificialanalysis.ai

FAQ

What is the cost per token for DeepSeek V4 Pro?
Input tokens cost $0.44 per 1M tokens; output tokens cost $0.87 per 1M tokens. There is no markup by OrcaRouter.
What is the context window size?
The context window is 1,048,576 tokens (approximately 1M tokens).
What is the maximum output length?
The model can generate up to 384,000 tokens in a single response.
What are the strengths of DeepSeek V4 Pro?
Its strengths include an extremely large context and output capacity, and a high score (96.2) on τ²-Bench, indicating strong agentic tool-use performance.
How does DeepSeek V4 Pro compare to other flagship models?
It has one of the largest context windows and output limits among flagships, but it is text-only. Its τ²-Bench score provides a direct comparison for agentic tasks, though no other benchmarks are specified here.
Does OrcaRouter add any markup to the pricing?
No, OrcaRouter bills at the provider rate with zero markup. You pay exactly $0.44/$0.87 per million tokens.
How do I call DeepSeek V4 Pro via OpenAI-compatible API?
Use base URL https://api.orcarouter.ai/v1, model ID 'deepseek/deepseek-v4-pro', and standard chat completions parameters.
What data handling or privacy policies apply?
No specific data handling details for this model have been provided. Check DeepSeek’s and OrcaRouter’s privacy policies for information on data usage.
Can DeepSeek V4 Pro handle images or audio?
No, it is a text-only model. It cannot process or generate multimodal inputs or outputs.
When should I choose a cheaper model instead?
For tasks with short contexts (<10K tokens) or simple queries, a cheaper model will be more cost-effective. Reserve DeepSeek V4 Pro for use cases that benefit from its huge context and output capacities.

Embed this badge

DeepSeek: DeepSeek V4 Pro$0.44/M in872ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/deepseek/deepseek-v4-pro" target="_blank"> <img src="https://www.orcarouter.ai/embed/deepseek/deepseek-v4-pro.svg" alt="DeepSeek: DeepSeek V4 Pro on OrcaRouter" /> </a>
Markdown [![DeepSeek: DeepSeek V4 Pro](https://www.orcarouter.ai/embed/deepseek/deepseek-v4-pro.svg)](https://www.orcarouter.ai/models/deepseek/deepseek-v4-pro)