DeepSeek V4 Pro 0813 by DeepSeek — Pricing, Benchmarks & Real Outputs
Share
Loading...
Compare DeepSeek V4 Pro 0813
Alternatives to DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813's competitors have been quietly putting in work.
DeepSeek V4 Pro 0813's competitors have been quietly putting in work.
DeepSeek V4 Pro 0813's competitors have been quietly putting in work.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek and the general-availability release of DeepSeek V4 Pro. It keeps the 1M-token context window and hybrid attention of the V4 line and is aimed at advanced reasoning, coding, and long-horizon agent workflows.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"deepseek/deepseek-v4-pro-0813" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
53 outputs · $1.95 tracked across 53 receipts
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek and the general-availability release of DeepSeek V4 Pro. It keeps the 1M-token context window and hybrid attention of the V4 line and is aimed at advanced reasoning, coding, and long-horizon agent workflows.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"deepseek/deepseek-v4-pro-0813" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
53 outputs · $1.95 tracked across 53 receipts