DeepSeekopen weightsDeepSeek V3 0324 pricing
$0.29 per 1M input tokens and $1.14 per 1M output tokens. In real work that is 0.72¢ per chat answer and 0.60¢ to summarize a 20-page PDF.
What DeepSeek V3 0324 costs per task
Token counts estimated from a measured model of the same lab (DeepSeek V4.1 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.72¢$7.22 / 1,000 | 65 in · 859 out · 5,461 reasoning | 259 of 336 | estimated |
| Reply to a customer email | 0.23¢$2.33 / 1,000 | 279 in · 225 out · 1,749 reasoning | 243 of 336 | estimated |
| Write a 1,500-word blog post | 0.35¢$3.49 / 1,000 | 81 in · 2,230 out · 809 reasoning | 101 of 336 | estimated |
| Write 10 product descriptions | 0.32¢$3.18 / 1,000 | 307 in · 870 out · 1,842 reasoning | 107 of 336 | estimated |
| Translate 1,000 words | 1.4¢$13.74 / 1,000 | 1,354 in · 1,417 out · 10,291 reasoning | 206 of 336 | estimated |
| Proofread one page (500 words) | 0.32¢$3.20 / 1,000 | 746 in · 660 out · 1,954 reasoning | 190 of 336 | estimated |
| Summarize a 20-page PDF | 0.60¢$6.03 / 1,000 | 12,970 in · 427 out · 1,565 reasoning | 148 of 336 | estimated |
| Extract data from an invoice | 0.34¢$3.40 / 1,000 | 395 in · 449 out · 2,436 reasoning | 201 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥2.0¢$19.63 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 160 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.53¢$5.35 / 1,000 | 3,696 in · 648 out · 3,102 reasoning | 177 of 336 | estimated |
| Classify 100 support tickets | 0.60¢$5.99 / 1,000 | 1,296 in · 461 out · 4,462 reasoning | 160 of 336 | estimated |
| Review 500 lines of code | ≥2.0¢$19.63 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 204 of 336 | estimated |
| Write a SQL query | 0.25¢$2.47 / 1,000 | 145 in · 406 out · 1,723 reasoning | 179 of 336 | estimated |
| Run a 50-step coding agent | 38¢$377 / 1,000 | 2,235,262 in · 14,985 out · 87,450 reasoning | 144 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving DeepSeek V3 0324 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 SiliconFlowfp8 | $0.25 / $1.00 | - | 163K | 100% |
| G GMICloudfp8 | $0.29 / $1.14 | $0.11 | 128K | 100% |
Price history
First seen in our price history on Mar 25, 2025 at $0.27 input / $1.10 output. Since then the output price moved from $1.10 to $1.14 per 1M tokens (17 changes).
FAQ
How much does DeepSeek V3 0324 cost?
DeepSeek V3 0324 costs $0.29 per 1 million input tokens and $1.14 per 1 million output tokens, with cached input at $0.11 (list price on Oct 18, 2026). In practice one chat answer costs about 0.72¢ and summarizing a 20-page PDF about 0.60¢.
Where is DeepSeek V3 0324 cheapest?
Among 2 providers we track, the lowest list price today is at SiliconFlow: $0.25 input and $1.00 output per 1M tokens.
Is the DeepSeek V3 0324 cost per task measured or estimated?
Estimated: DeepSeek V3 0324 was not run directly. Tokens come from DeepSeek V4.1 Flash and are rescaled by the tokenizer of DeepSeek. Real usage can differ.