DeepSeekopen weightsDeepSeek V3 pricing
$0.32 per 1M input tokens and $0.89 per 1M output tokens. In real work that is 0.56¢ per chat answer and 0.59¢ to summarize a 20-page PDF.
What DeepSeek V3 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 | 0.56¢$5.65 / 1,000 | 65 in · 859 out · 5,461 reasoning | 234 of 336 | estimated |
| Reply to a customer email | 0.18¢$1.85 / 1,000 | 279 in · 225 out · 1,749 reasoning | 224 of 336 | estimated |
| Write a 1,500-word blog post | 0.27¢$2.73 / 1,000 | 81 in · 2,230 out · 809 reasoning | 80 of 336 | estimated |
| Write 10 product descriptions | 0.25¢$2.51 / 1,000 | 307 in · 870 out · 1,842 reasoning | 94 of 336 | estimated |
| Translate 1,000 words | 1.1¢$10.85 / 1,000 | 1,354 in · 1,417 out · 10,291 reasoning | 188 of 336 | estimated |
| Proofread one page (500 words) | 0.26¢$2.57 / 1,000 | 746 in · 660 out · 1,954 reasoning | 171 of 336 | estimated |
| Summarize a 20-page PDF | 0.59¢$5.92 / 1,000 | 12,970 in · 427 out · 1,565 reasoning | 146 of 336 | estimated |
| Extract data from an invoice | 0.27¢$2.69 / 1,000 | 395 in · 449 out · 2,436 reasoning | 186 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.6¢$15.78 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 134 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.45¢$4.52 / 1,000 | 3,696 in · 648 out · 3,102 reasoning | 162 of 336 | estimated |
| Classify 100 support tickets | 0.48¢$4.80 / 1,000 | 1,296 in · 461 out · 4,462 reasoning | 139 of 336 | estimated |
| Review 500 lines of code | ≥1.6¢$15.78 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 189 of 336 | estimated |
| Write a SQL query | 0.19¢$1.94 / 1,000 | 145 in · 406 out · 1,723 reasoning | 154 of 336 | estimated |
| Run a 50-step coding agent | 81¢$806 / 1,000 | 2,235,262 in · 14,985 out · 87,450 reasoning | 216 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving DeepSeek V3 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp4 | $0.26 / $0.71 | - | 163K | |
DeepInfrafp4 | $0.32 / $0.89 | - | 163K | 93% |
| S StreamLakeunknown | $0.26 / $1.03 | - | 128K | 100% |
Price history
First seen in our price history on Jun 19, 2024 at $0.14 input / $0.28 output. Since then the output price moved from $0.28 to $0.89 per 1M tokens (24 changes).
FAQ
How much does DeepSeek V3 cost?
DeepSeek V3 costs $0.32 per 1 million input tokens and $0.89 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.56¢ and summarizing a 20-page PDF about 0.59¢.
Where is DeepSeek V3 cheapest?
Among 3 providers we track, the lowest list price today is at DeepInfra: $0.26 input and $0.71 output per 1M tokens.
Is the DeepSeek V3 cost per task measured or estimated?
Estimated: DeepSeek V3 was not run directly. Tokens come from DeepSeek V4.1 Flash and are rescaled by the tokenizer of DeepSeek. Real usage can differ.