DeepSeekopen weightsDeepSeek V3.2 pricing
$0.28 per 1M input tokens and $0.42 per 1M output tokens. In real work that is 0.27¢ per chat answer and 0.45¢ to summarize a 20-page PDF.
What DeepSeek V3.2 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 | 0.27¢$2.67 / 1,000 | 65 in · 859 out · 5,461 reasoning | 181 of 336 | estimated |
| Reply to a customer email | 0.09¢$0.91 / 1,000 | 279 in · 225 out · 1,749 reasoning | 164 of 336 | estimated |
| Write a 1,500-word blog post | 0.13¢$1.30 / 1,000 | 81 in · 2,230 out · 809 reasoning | 33 of 336 | estimated |
| Write 10 product descriptions | 0.12¢$1.22 / 1,000 | 307 in · 870 out · 1,842 reasoning | 36 of 336 | estimated |
| Translate 1,000 words | 0.53¢$5.30 / 1,000 | 1,354 in · 1,417 out · 10,291 reasoning | 140 of 336 | estimated |
| Proofread one page (500 words) | 0.13¢$1.31 / 1,000 | 746 in · 660 out · 1,954 reasoning | 111 of 336 | estimated |
| Summarize a 20-page PDF | 0.45¢$4.47 / 1,000 | 12,970 in · 427 out · 1,565 reasoning | 117 of 336 | estimated |
| Extract data from an invoice | 0.13¢$1.32 / 1,000 | 395 in · 449 out · 2,436 reasoning | 124 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.81¢$8.06 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 92 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.26¢$2.61 / 1,000 | 3,696 in · 648 out · 3,102 reasoning | 116 of 336 | estimated |
| Classify 100 support tickets | 0.24¢$2.43 / 1,000 | 1,296 in · 461 out · 4,462 reasoning | 87 of 336 | estimated |
| Review 500 lines of code | ≥0.81¢$8.06 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 128 of 336 | estimated |
| Write a SQL query | 0.09¢$0.93 / 1,000 | 145 in · 406 out · 1,723 reasoning | 99 of 336 | estimated |
| Run a 50-step coding agent | 13¢$126 / 1,000 | 2,235,262 in · 14,985 out · 87,450 reasoning | 70 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving DeepSeek V3.2 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| G GMICloudfp8 | $0.21 / $0.31 | $0.022 | 163K | 100% |
 DeepInfrafp4 | $0.26 / $0.38 | $0.13 | 163K | 100% |
| A AtlasCloudfp8 | $0.26 / $0.38 | $0.13 | 163K | 100% |
| V Veniceunknown | $0.27 / $0.39 | $0.13 | 160K | 100% |
| B Baidufp8 | $0.28 / $0.42 | $0.028 | 131K | 100% |
 SiliconFlowfp8 | $0.26 / $0.80 | $0.14 | 163K | 100% |
| D DigitalOceanunknown | $0.30 / $0.96 | $0.09 | 163K | 100% |
| P Phalaunknown | $1.00 / $1.00 | $0.50 | 163K | 100% |
| F Friendliunknown | $0.50 / $1.50 | $0.25 | 163K | 100% |
 Googleunknown | $0.56 / $1.68 | - | 163K | 100% |
| M Maraunknown | $3.00 / $4.50 | - | 32K | |
 SambaNovaunknown | $3.00 / $4.50 | - | 32K | 100% |
Price history
First seen in our price history on Dec 6, 2025 at $0.27 input / $0.40 output. Since then the output price moved from $0.40 to $0.42 per 1M tokens (15 changes).
FAQ
How much does DeepSeek V3.2 cost?
DeepSeek V3.2 costs $0.28 per 1 million input tokens and $0.42 per 1 million output tokens, with cached input at $0.028 (list price on Oct 18, 2026). In practice one chat answer costs about 0.27¢ and summarizing a 20-page PDF about 0.45¢.
Where is DeepSeek V3.2 cheapest?
Among 12 providers we track, the lowest list price today is at GMICloud: $0.21 input and $0.31 output per 1M tokens.
Is the DeepSeek V3.2 cost per task measured or estimated?
Estimated: DeepSeek V3.2 was not run directly. Tokens come from DeepSeek V4.1 Flash and are rescaled by the tokenizer of DeepSeek. Real usage can differ.