DeepSeek V3 0324
by DeepSeek · deepseek/deepseek-chat-v3-0324 · #145 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.25
per 1M tokens
Output
$1.00
per 1M tokens
Blended (3:1)
$0.438
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V3 0324 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.438 | $0.0265 | — |
| 50% | $0.438 | $0.0265 | −0% |
| 90% | $0.438 | $0.0265 | −0% |
*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 | $0.000425 | $0.425 |
| Document summary | 8,000 | 1,000 | $0.003 | $3.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0095 | $9.50 |
| Long-context analysis | 150,000 | 5,000 | $0.0425 | $42.50 |
Performance
Intelligence Index
9.7
AA composite quality
Coding Index
21.2
Math Index
41
Agentic Index
0.8
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 81.9% |
| GPQA Diamond | 65.5% |
| Humanity's Last Exam | 4.7% |
| LiveCodeBench | 40.5% |
| SciCode | 39.0% |
| MATH-500 | 94.2% |
| AIME | 52.0% |
| AIME 2025 | 41.0% |
| IFBench | 41.0% |
| AA-LCR (Long Context Reasoning) | 40.7% |
| Terminal-Bench Hard | 15.2% |
| Terminal-Bench 2.1 | 13.9% |
| τ²-Bench (Telecom) | 47.1% |
| τ³-Bench Banking | 4.7% |
Specs
Context window
164K
tokens
Max output
147K
tokens
Input modalities
text
Tokenizer
DeepSeek