DeepSeek V4 Pro 0813
by DeepSeek · deepseek/deepseek-v4-pro-0813 · #258 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:29 PM UTC · refreshed nightly
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.111
per 1M tokens
Output
$4.44
per 1M tokens
Blended (3:1)
$1.19
3 input : 1 output
Cache read
$0.097
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V4 Pro 0813 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.19 | $0.0158 | — |
| 50% | $1.19 | $0.0151 | −4% |
| 90% | $1.18 | $0.0145 | −8% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.001387 | $1.39 |
| Document summary | 8,000 | 1,000 | $0.005328 | $5.33 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0122 | $12.21 |
| Long-context analysis | 150,000 | 5,000 | $0.0388 | $38.85 |
Performance
Intelligence Index
23.1
AA composite quality
Coding Index
68.8
Math Index
—
Agentic Index
41.3
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
1.05M
tokens
Max output
944K
tokens
Input modalities
text
Tokenizer
DeepSeek