DeepSeekopen weightsDeepSeek V4.1 Flash pricing
$0.072 per 1M input tokens and $0.14 per 1M output tokens. In real work that is 0.09¢ per chat answer and 0.12¢ to summarize a 20-page PDF.
Official price at DeepSeek: $0.30 / $1.20 per 1M, cached $0.006 (source, verified Oct 18, 2026). OpenRouter lists $0.072 / $0.14, which is the cheapest route across its hosts - lower than the official price.
What DeepSeek V4.1 Flash costs per task
Every row below was measured: we ran the task on this model and counted the tokens. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.09¢$0.91 / 1,000 | 65 in · 859 out · 5,461 reasoning | 96 of 336 | measured |
| Reply to a customer email | 0.03¢$0.30 / 1,000 | 279 in · 225 out · 1,749 reasoning | 78 of 336 | measured |
| Write a 1,500-word blog post | 0.04¢$0.44 / 1,000 | 81 in · 2,230 out · 809 reasoning | 7 of 336 | measured |
| Write 10 product descriptions | 0.04¢$0.41 / 1,000 | 307 in · 870 out · 1,842 reasoning | 10 of 336 | measured |
| Translate 1,000 words | 0.18¢$1.78 / 1,000 | 1,354 in · 1,417 out · 10,291 reasoning | 95 of 336 | measured |
| Proofread one page (500 words) | 0.04¢$0.43 / 1,000 | 746 in · 660 out · 1,954 reasoning | 39 of 336 | measured |
| Summarize a 20-page PDF | 0.12¢$1.22 / 1,000 | 12,970 in · 427 out · 1,565 reasoning | 26 of 336 | measured |
| Extract data from an invoice | 0.04¢$0.44 / 1,000 | 395 in · 449 out · 2,436 reasoning | 43 of 336 | measured |
| Analyze a 200-row spreadsheet | ≥0.26¢$2.65 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 30 of 336 | measured |
| Answer from 5 retrieved documents (RAG) | 0.08¢$0.81 / 1,000 | 3,696 in · 648 out · 3,102 reasoning | 38 of 336 | measured |
| Classify 100 support tickets | 0.08¢$0.80 / 1,000 | 1,296 in · 461 out · 4,462 reasoning | 22 of 336 | measured |
| Review 500 lines of code | ≥0.26¢$2.65 / 1,000 | 4,801 in · 0 out · 16,000 reasoning | 31 of 336 | measured |
| Write a SQL query | 0.03¢$0.32 / 1,000 | 145 in · 406 out · 1,723 reasoning | 18 of 336 | measured |
| Run a 50-step coding agent | 2.4¢$24.06 / 1,000 | 2,235,262 in · 14,985 out · 87,450 reasoning | 7 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving DeepSeek V4.1 Flash through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| O OpenInferencefp4 | $0.072 / $0.14 | $0.002 | 1M | 100% |
| D Decartfp4 | $0.09 / $0.18 | $0.018 | 1M | 100% |
| S Sail Researchfp4 | $0.09 / $0.30 | $0.006 | 1M | 100% |
 DeepInfrafp8 | $0.11 / $0.34 | $0.003 | 1M | 100% |
DeepInfrafp8 | $0.14 / $0.42 | $0.004 | 1M | 100% |
| M Morphfp8 | $0.09 / $0.55 | $0.008 | 1M | 100% |
| A AtlasCloudfp8 | $0.14 / $0.54 | $0.013 | 1M | 100% |
| S StreamLakefp8 | $0.15 / $0.60 | $0.003 | 1M | 100% |
| R Relaceunknown | $0.20 / $0.60 | $0.008 | 1M | 100% |
| W Wafermxfp4 | $0.10 / $0.65 | $0.006 | 1M | 100% |
| C CoreWeavefp8 | $0.15 / $0.65 | $0.002 | 1M | 100% |
DeepInfrafp8 | $0.21 / $0.63 | $0.006 | 1M | 100% |
| I InferenceNetfp8 | $0.10 / $0.71 | $0.008 | 1M | 100% |
| G GMICloudfp8 | $0.18 / $0.72 | $0.004 | 1M | 100% |
| D DigitalOceanunknown | $0.20 / $0.78 | $0.006 | 1M | 100% |
 Novitafp8 | $0.20 / $0.78 | $0.004 | 1M | 100% |
| P Phalaunknown | $0.21 / $0.84 | $0.004 | 1M | 100% |
| M Makorafp8 | $0.27 / $1.15 | $0.009 | 1M | 100% |
| I Ionstreamunknown | $0.27 / $1.20 | $0.006 | 1M | 100% |
| C Crusoefp8 | $0.29 / $1.20 | $0.007 | 1M | 100% |
 Nebiusfp8 | $0.30 / $1.20 | - | 1M | 100% |
| P PrimeIntellectunknown | $0.30 / $1.20 | $0.03 | 1M | 100% |
| B Baidufp8 | $0.30 / $1.20 | $0.006 | 1M | 100% |
| B BaseTenunknown | $0.30 / $1.20 | $0.007 | 1M | 100% |
 Alibabaunknown | $0.30 / $1.20 | $0.03 | 1M | 100% |
 Togetherunknown | $0.30 / $1.20 | $0.006 | 1M | 100% |
 SiliconFlowfp8 | $0.30 / $1.20 | $0.006 | 1M | 100% |
| M Modalunknown | $0.30 / $1.20 | $0.03 | 1M | 100% |
| B BaseTenunknown | $0.30 / $1.20 | $0.007 | 1M | 100% |
 Parasailfp8 | $0.30 / $1.20 | $0.006 | 1M | 100% |
 Fireworksunknown | $0.30 / $1.20 | $0.006 | 1M | 100% |
| V Venicefp8 | $0.30 / $1.20 | $0.007 | 1M | 100% |
Fireworksunknown | $0.45 / $1.80 | $0.009 | 1M | |
| B BaseTenunknown | $0.60 / $2.40 | $0.014 | 1M | 100% |
Price history
First seen in our price history on Sep 14, 2026 at $0.15 input / $0.60 output. Since then the output price moved from $0.60 to $0.14 per 1M tokens (5 changes).
FAQ
How much does DeepSeek V4.1 Flash cost?
DeepSeek V4.1 Flash costs $0.072 per 1 million input tokens and $0.14 per 1 million output tokens, with cached input at $0.002 (list price on Oct 18, 2026). In practice one chat answer costs about 0.09¢ and summarizing a 20-page PDF about 0.12¢.
Where is DeepSeek V4.1 Flash cheapest?
Among 34 providers we track, the lowest list price today is at OpenInference: $0.072 input and $0.14 output per 1M tokens.
Does DeepSeek V4.1 Flash charge for reasoning tokens?
Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.
Is the DeepSeek V4.1 Flash cost per task measured or estimated?
Measured: we ran all 13 benchmark prompts on DeepSeek V4.1 Flash through OpenRouter and recorded the tokens it used.