LLM prices / DeepSeek / DeepSeek V4 Pro
DeepSeek API · prices checked Oct 23, 2026
DeepSeek V4 Pro API pricing
Short answerDeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens on the DeepSeek API (standard price, checked Oct 23, 2026). A typical chatbot reply (1,500 tokens in, 400 out) costs $0.0036, so 1,000 replies a day is about $107 a month and 1M replies is $3,564. That makes it #11 cheapest of the 29 current models for that job.
Best for
- Long repeated prompts (agents, RAG with a fixed prefix): cached input bills at 3% of the normal input price.
- Whole codebases or contracts in one prompt: 1M tokens of context.
Skip if
- You need image input: the provider lists text input only.
- You run large offline jobs: no batch price is listed.
Rules: Best for = cheapest quarter of current models for a chatbot reply, top 3 on one of our 8 jobs, cache reads at 15% or less of input, batch at 60% or less, 1M+ context, non-text inputs. Skip if = not current on the provider's page, priciest quarter, text only, no cache or batch price, a long-prompt surcharge, preview, under 200K context, no tool calling. Price and spec facts only; we don't score answer quality.
What your volume costs
Pick a job and a monthly volume. Same prices as everything on this page; caching and batch applied where they make it cheaper.
Cost per task, 8 jobs
Per 1,000 requests and per month at a typical volume, billed the cheapest way the price list allows. The rank is among current models that fit the job.
| Job (links to the cheapest model for it) | Per 1,000 | A month | Rank among fits |
|---|---|---|---|
| Chatbota 1,500-token prompt (system prompt plus the conversation so far) and a 400-token reply | $3.56standard price | $107at 30,000 a month | #11 of 29 |
| RAG (answer from your docs)6,000 tokens of retrieved passages plus the question, and a 500-token answer | $9.90standard price | $297at 30,000 a month | #11 of 29 |
| Coding agent40,000 tokens of repo context and history, 30,000 of them repeated from the last step and billed at the cache-read price, 2,000 tokens out, tool calling required | $22.44with the repeated 30,000 tokens billed at the cache-read price | $67.32at 3,000 a month | #11 of 29 |
| Tool-using agent12,000 tokens of instructions, tool definitions and history, 10,000 of them repeated from the last step and cached, 600 tokens out, tool calling required | $5.46with the repeated 10,000 tokens billed at the cache-read price | $54.56at 10,000 a month | #11 of 29 |
| Vision (read an image)one image counted as 1,000 input tokens plus a 300-token question, and a 300-token answer. Providers count image tokens differently, so treat vision costs as a rough guide | $2.90standard price | $29.04at 10,000 a month | does not fit |
| Translationa 1,000-token passage in and about 1,100 tokens out (translations run a little longer than the source) | $5.68standard price | $56.76at 10,000 a month | tied #10 of 29 |
| Batch extraction2,000 tokens per record in and 300 tokens of JSON out, through the batch API where there is one (results within 24 hours) | $3.83standard price | $383at 100,000 a month | #17 of 29 |
| Summarize long documentsa 20,000-token document in and an 800-token summary out | $29.57standard price | $29.57at 1,000 a month | #11 of 29 |
Cheaper and pricier alternatives
The current models just below and just above DeepSeek V4 Pro on the cost of 1,000 chatbot replies, with what differs. Price only, not quality.
Cheaper
- GPT-5.4 mini $2.930.82x the cost of a chatbot reply, OpenAI, 400K context vs 1M, takes image too, has a batch price.
- Gemini 3.8 Flash $2.620.74x the cost of a chatbot reply, Google, 1.05M context vs 1M, takes image, video, audio, pdf too, has a batch price.
- Gemini 3.6 Flash $2.620.74x the cost of a chatbot reply, Google, 1.05M context vs 1M, takes image, video, audio, pdf too, has a batch price.
Pricier
- Claude Sonnet 5.5 $7.001.96x the cost of a chatbot reply, Anthropic, takes image too, has a batch price.
- GPT-6.1 Sol $7.001.96x the cost of a chatbot reply, OpenAI, 1.05M context vs 1M, takes image too, has a batch price.
- GPT-6 Sol $7.001.96x the cost of a chatbot reply, OpenAI, 1.05M context vs 1M, takes image too, has a batch price.
Every price tier
| Input | $1.32 per 1M tokens |
| Output | $3.96 per 1M tokens |
| Cache read (hit) | $0.044 (3% of the input price) |
| Offpeak tier | $0.66 input / $1.98 output |
| API model id | deepseek-v4-pro |
| Status on the pricing page | listed |
Provider notes: input/output/cache_read are peak-hour prices; other_tiers.offpeak is the off-peak price (peak hours: 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays); null means the page lists no price: batch_input, batch_output
Model facts from DeepSeek
| Context window | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Input types | text |
| Tool calling | yes |
| Lifecycle | current |
| Provider note | Page states context length 1M and max output maximum 384K; model version DeepSeek-V4-Pro-0813; Vision not supported. |
Source: https://api-docs.deepseek.com/quick_start/pricing/, checked Oct 24, 2026.
The 6 classic workloads
Per 1,000 requests at the standard price. "With caching" bills the repeated part of the prompt at the cache-read price (cache writes not counted); "via batch" uses the batch API price. Run your own token counts in the LLM API cost calculator.
| Workload | DeepSeek V4 Proper 1,000 requests |
|---|---|
| Chatbot replya 1,500-token prompt (1,000 of it a fixed system prompt) and a 400-token answer | $3.56$2.29 with caching |
| Answer from your docs (RAG)6,000 tokens of retrieved context plus the question, a 500-token answer | $9.90$8.62 with caching |
| Summarize a long documenta 20,000-token document in, an 800-token summary out | $29.57$28.29 with caching |
| Coding agent step40,000 tokens of repo context and history (30,000 of it repeated from the last step), 2,000 out | $60.72$22.44 with caching |
| Batch extraction2,000 tokens per record in, 300 tokens of JSON out, sent through the batch API where there is one | $3.83 |
| Long-document Q&Aa 150,000-token contract or codebase in one prompt, a 1,000-token answer | $202 |
What the numbers say
- Output costs 3x input on DeepSeek V4 Pro, so for answer-heavy jobs the output price drives the bill; for document-heavy jobs (RAG, summaries, agents) input does.
- Caching matters: a coding-agent step that rereads 30,000 cached tokens costs 63% less than the same step uncached ($22.44 vs $60.72 per 1,000 steps, cache writes not counted). How to stop paying twice for repeated prompts: LLM semantic cache.
- Among 2 listed DeepSeek models it is the most expensive for a chat reply.
Every listed DeepSeek model, cheapest first
Same chatbot workload, 1,000 replies.
| Model | Input / 1M | Output / 1M | 1,000 chat replies |
|---|---|---|---|
| DeepSeek Flash | $0.3 | $1.2 | $0.93 |
| DeepSeek V4 Pro | $1.32 | $3.96 | $3.56 |
Closest price from other providers
The current model from each other provider whose chatbot-reply cost is nearest. Price only: we do not rank quality here.
| Model | Input / 1M | Output / 1M | 1,000 chat replies | vs DeepSeek V4 Pro |
|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.1 | $0.5 | $0.35 | 0.10x |
| GPT-5.4 miniOpenAI | $0.75 | $4.5 | $2.93 | 0.82x |
| Gemini 3.8 FlashGoogle | $0.75 | $3.75 | $2.62 | 0.74x |
Price history
- Oct 23, 2026: DeepSeek V4 Pro added to the table: $1.32 input / $3.96 output per 1M tokens.
- Checked against the provider page on 1 date: Oct 23, 2026.
Every change we record is on the LLM price changelog.
Sources
- DeepSeek API pricing: https://api-docs.deepseek.com/quick_start/pricing, checked Oct 23, 2026.
- Context, inputs and lifecycle: https://api-docs.deepseek.com/quick_start/pricing/, checked Oct 24, 2026.
- Dataset: llm-prices (every row names its page and check date) and /llm/prices.csv.
Prices change often. If one is out of date, email matt@tensorust.com and we will fix it.