DeepSeek V4 Pro 0423
by DeepSeek · deepseek/deepseek-v4-pro · #168 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.422
per 1M tokens
Output
$0.845
per 1M tokens
Blended (3:1)
$0.528
3 input : 1 output
Cache read
$0.035
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V4 Pro 0423 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.528 | $0.0439 | — |
| 50% | $0.383 | $0.0246 | −44% |
| 90% | $0.267 | $0.009079 | −79% |
*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 | $0.000465 | $0.4645 |
| Document summary | 8,000 | 1,000 | $0.004223 | $4.22 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0144 | $14.36 |
| Long-context analysis | 150,000 | 5,000 | $0.0676 | $67.57 |
Performance
Intelligence Index
36
AA composite quality
Coding Index
68.8
Math Index
—
Agentic Index
27.7
Output speed
85 tok/s
median
Time to first token
1.08s
median
Time to first answer
24.59s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 92.8% |
| Humanity's Last Exam | 41.0% |
| SciCode | 51.0% |
| AA-LCR (Long Context Reasoning) | 80.3% |
| Terminal-Bench 2.1 | 78.7% |
| τ³-Bench Banking | 39.6% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,247 |
| Web apps | 1,000 |
| Full-stack | 948 |
| UI components | 1,237 |
| Data viz | 1,218 |
| SVG | 1,164 |
| 3D | 1,283 |
| Game dev | 1,252 |
| Godot game dev | 1,059 |
| Code categories | 1,256 |
| ASCII art | 1,168 |
Specs
Context window
1.05M
tokens
Max output
384K
tokens
Input modalities
text
Tokenizer
DeepSeek