Pricing · DeepSeek
DeepSeek V4.1 Flash pricing: API price, cost per message and plans
What DeepSeek V4.1 Flash costs, three ways: DeepSeek's API price per token, what DeepSeek V4.1 Flash's replies actually cost in our test runs, and how many DeepSeek V4.1 Flash messages each llmwise plan includes. Every limit on DeepSeek V4.1 Flash is on its model page.
API prices checked against OpenRouter's DeepSeek V4.1 Flash page. Updated .
Short answer
DeepSeek V4.1 Flash's API price is $0.30 per million input tokens and $1.20 per million output tokens (the price of the OpenRouter endpoints llmwise uses, not DeepSeek's own API, October 2026). In our 50 test runs a DeepSeek V4.1 Flash reply cost $0.00052 on average (median $0.00030), from $0.00017 a reply on RAG and answering from documents to $0.0018 on coding. In llmwise you pay per message instead: up to 30 DeepSeek V4.1 Flash messages a day on Plus ($10), 60 on Pro ($20), 120 on Max ($50), 200 on Ultra ($100) and 200 on Studio ($200).
DeepSeek V4.1 Flash API pricing
DeepSeek V4.1 Flash through its API is billed per token: $0.30 in, $1.20 out per million tokens, as of October 2026.
| Input tokens | $0.30 per million |
|---|---|
| Output tokens | $1.20 per million |
| A typical DeepSeek V4.1 Flash message (4,000 in, 700 out) | $0.0020 |
| 1,000 typical DeepSeek V4.1 Flash messages | $2.04 |
| Typical DeepSeek V4.1 Flash messages for $1 | 490 |
| Whose price | the price of the OpenRouter endpoints llmwise uses, not DeepSeek's own API |
What a DeepSeek V4.1 Flash reply cost in our test runs
We sent the same 50 test prompts to every model in llmwise on October 8, 2026, through OpenRouter with llmwise's own prompt and settings. Here's what each DeepSeek V4.1 Flash reply cost, job by job.
| Job | DeepSeek V4.1 Flash, per reply | Per 1,000 replies | Tokens in / out | Passed |
|---|---|---|---|---|
| Coding | $0.0018 | $1.83 | 526 / 1,459 | 5 of 5 |
| Writing | $0.00045 | $0.45 | 438 / 316 | 4 of 5 |
| Math | $0.00025 | $0.25 | 435 / 162 | 5 of 5 |
| Summarization | $0.00020 | $0.20 | 538 / 96 | 5 of 5 |
| Data analysis | $0.00085 | $0.85 | 623 / 613 | 5 of 5 |
| Customer support | $0.00046 | $0.46 | 561 / 332 | 4 of 5 |
| Translation | $0.00058 | $0.58 | 475 / 427 | 5 of 5 |
| SQL | $0.00020 | $0.20 | 541 / 120 | 5 of 5 |
| RAG and answering from documents | $0.00017 | $0.17 | 692 / 79 | 5 of 5 |
| Agents and tool use | $0.00020 | $0.20 | 522 / 102 | 5 of 5 |
Across all 50 DeepSeek V4.1 Flash replies: $0.00052 on average, $0.00030 at the median, $0.000068 for the cheapest and $0.0042 for the dearest. The DeepSeek V4.1 Flash replies averaged 535 tokens in and 371 out, against the typical message's 4,000 in and 700 out: each test prompt starts a new chat, while a reply deep in a long chat rereads all of it.
DeepSeek V4.1 Flash on each llmwise plan
In llmwise a DeepSeek V4.1 Flash message is one of a published count, however long the reply runs, and you see what's left before you send.
Free: DeepSeek V4.1 Flash isn't in the one-time trial of 5 messages; it takes a paid plan.
Plus, $10 a month: up to 30 DeepSeek V4.1 Flash messages a day, on top of the monthly allowance the other models share.
Pro, $20 a month: up to 60 DeepSeek V4.1 Flash messages a day, on top of the monthly allowance the other models share.
Max, $50 a month: up to 120 DeepSeek V4.1 Flash messages a day, on top of the monthly allowance the other models share.
Ultra, $100 a month: up to 200 DeepSeek V4.1 Flash messages a day, on top of the monthly allowance the other models share.
Studio, $200 a month: up to 200 DeepSeek V4.1 Flash messages a day, on top of the monthly allowance the other models share.
A $10 top-up doesn't add DeepSeek V4.1 Flash messages: it tops up the monthly allowance, and DeepSeek V4.1 Flash runs on its own daily count.
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
DeepSeek V4.1 Flash against the other DeepSeek models
Every DeepSeek model in llmwise beside DeepSeek V4.1 Flash, dearest first.
| Model | API, per 1M in / out | Input price against DeepSeek V4.1 Flash | Average reply in our runs | On Pro |
|---|---|---|---|---|
| DeepSeek V4 ProDeepSeek | $0.40 / $4.00 | 1.3 times DeepSeek V4.1 Flash's | $0.0037 | Up to 250 a month |
| DeepSeek V4.1 FlashDeepSeekThis page | $0.30 / $1.20 | – | $0.00052 | Up to 60 a day |
DeepSeek V4.1 Flash's own page: DeepSeek V4.1 Flash: price, limits and messages on every plan. DeepSeek V4.1 Flash passed 48 of the 50 test prompts these costs come from.
Questions
How much does a DeepSeek V4.1 Flash message cost?
In our test runs, $0.00052 a reply on average through OpenRouter (median $0.00030), across 50 DeepSeek V4.1 Flash replies to our test prompts. At the API price a typical DeepSeek V4.1 Flash message of 4,000 tokens in and 700 out costs $0.0020; a long chat costs more, because every reply rereads it.
What is DeepSeek V4.1 Flash's API price?
$0.30 per million input tokens and $1.20 per million output tokens, as of October 2026 (the price of the OpenRouter endpoints llmwise uses, not DeepSeek's own API).
How many DeepSeek V4.1 Flash messages does llmwise Pro include?
Up to 60 DeepSeek V4.1 Flash messages a day on Pro ($20 a month), refilled at 00:00 UTC, on top of the monthly allowance.
Can I use DeepSeek V4.1 Flash for free?
Not in llmwise's free trial, which is Claude Haiku 5.5 alone; DeepSeek V4.1 Flash takes a paid plan.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.