DeepSeek V3.2 Exp
by DeepSeek · deepseek/deepseek-v3.2-exp · #86 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:26 AM UTC · refreshed hourly
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.27
per 1M tokens
Output
$0.41
per 1M tokens
Blended (3:1)
$0.305
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V3.2 Exp (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.305 | $0.028 | — |
| 50% | $0.305 | $0.028 | −0% |
| 90% | $0.305 | $0.028 | −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 | $0.000258 | $0.258 |
| Document summary | 8,000 | 1,000 | $0.00257 | $2.57 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00892 | $8.92 |
| Long-context analysis | 150,000 | 5,000 | $0.0426 | $42.55 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,206 |
| UI components | 1,208 |
| Data viz | 1,189 |
| SVG | 1,079 |
| 3D | 1,207 |
| Game dev | 1,203 |
| Code categories | 1,204 |
Specs
Context window
164K
tokens
Max output
66K
tokens
Input modalities
text
Tokenizer
DeepSeek