DeepSeek V3
by DeepSeek · deepseek/deepseek-chat · #160 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:41 PM UTC · refreshed nightly
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.257
per 1M tokens
Output
$1.03
per 1M tokens
Blended (3:1)
$0.45
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V3 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.45 | $0.0273 | — |
| 50% | $0.45 | $0.0273 | −0% |
| 90% | $0.45 | $0.0273 | −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 | $0.000437 | $0.4373 |
| Document summary | 8,000 | 1,000 | $0.003088 | $3.09 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.009779 | $9.78 |
| Long-context analysis | 150,000 | 5,000 | $0.0438 | $43.75 |
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 | 1,112 |
| UI components | 1,082 |
| Data viz | 1,085 |
| SVG | 965 |
| 3D | 1,067 |
| Game dev | 1,043 |
| Code categories | 1,097 |
Specs
Context window
164K
tokens
Max output
16K
tokens
Input modalities
text
Tokenizer
DeepSeek