DeepSeek · Model
DeepSeek V4 Pro 0813 pricing, context window and specs
DeepSeek V4 Pro 0813 costs $1.32 per million input tokens and $3.96 per million output tokens, and reads up to 1,048,576 tokens per request. By blended price it is the most expensive of DeepSeek’s 4 current models here.
- Input / 1M
- $1.32
- Output / 1M
- $3.96
- Cached / 1M
- $0.044
- Context
- 1,048,576
- Max output
- 393,216
- Released
- 2026-08-12
This is DeepSeek’s peak-hour price (01:00–04:00 and 06:00–10:00 UTC on weekdays). At all other times, including weekends and Chinese public holidays, DeepSeek charges half: $0.66 input and $1.98 output per million tokens. DeepSeek API pricing, checked 2026-10-11.
Estimate your cost with DeepSeek V4 Pro 0813Compare all DeepSeek modelsCount tokens for DeepSeek V4 Pro 0813
Pricing
DeepSeek V4 Pro 0813 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $1.32 | $3.96 |
| Cached input (read) | $0.044 | – |
Output costs 3.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 3% of the normal input price.
Examples
What DeepSeek V4 Pro 0813 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00261 | $79.30 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00837 | $127.28 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0199 | $120.99 |
| Document summariser | 8,000 / 600 | 300 | $0.0129 | $118.04 |
Change any number in the cost calculator.
Context
Context window
DeepSeek V4 Pro 0813 accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 393,216 tokens.
Filling the whole window with one prompt costs about $1.38 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- No
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
DeepSeek V4 Pro 0813 model ID
- OpenRouter
deepseek/deepseek-v4-pro-0813- DeepSeek API
deepseek-v4-pro(alias)- Open weights
- deepseek-ai/DeepSeek-V4-Pro-0813
DeepSeek lists DeepSeek V4 Pro 0813 as current. Every DeepSeek model ID, with aliases and snapshots.
DeepSeek
Where DeepSeek V4 Pro 0813 sits in DeepSeek’s line-up
Ranked by blended price (three parts input to one part output, $1.98 per 1M for DeepSeek V4 Pro 0813), it is the most expensive of DeepSeek’s 4 current models here. One step down, DeepSeek V4.1 Flash costs $0.525 blended (73% less). Unlike DeepSeek V4 Pro 0813, it accepts images. See every DeepSeek model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | $0.2088 | $0.4176 | 1,024,000 | 2026-04-24 |
| DeepSeek V3.2 | $0.259 | $0.80 | 163,840 | 2025-12-01 |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | 1,048,576 | 2026-09-10 |
| DeepSeek V4 Pro 0813 (this page) | $1.32 | $3.96 | 1,048,576 | 2026-08-12 |
DeepSeek’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of DeepSeek V4 Pro 0813
The previous model in this line is DeepSeek V4 Pro 0423, first listed on 2026-04-24. Compared with it, DeepSeek V4 Pro 0813’s input price is 532% higher and its output price is 848% higher, and the context window went from 1,024,000 to 1,048,576 tokens.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | $0.2088 | $0.4176 | 1,024,000 | 2026-04-24 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- GPT-6 LunaOpenAI90% cheaper
- Claude Haiku 5.5Anthropic90% cheaper
- Qwen3.8 Omni FlashQwen88% cheaper
- DeepSeek V4 Pro 0423DeepSeek87% cheaper
- GLM 4.6VZ.ai77% cheaper
Current models from major providers, one per provider, that keep tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Muse Spark 1.3Meta$1.25 / $4.25
- GLM 5V TurboZ.ai$1.20 / $4
- GPT-5.4 MiniOpenAI$0.75 / $4.50
- Gemini 3.8 FlashGoogle$0.75 / $3.75
- Kimi K2.7 CodeMoonshot AI$0.6712 / $3.35
Current models from other major providers, closest blended price.
FAQ
DeepSeek V4 Pro 0813 questions
How much does DeepSeek V4 Pro 0813 cost?
DeepSeek V4 Pro 0813 costs $1.32 per million input tokens and $3.96 per million output tokens, with cached input at $0.044. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00356. Use the LLM cost calculator for your own workload. This is DeepSeek’s peak-hour price (01:00–04:00 and 06:00–10:00 UTC on weekdays). At all other times, including weekends and Chinese public holidays, DeepSeek charges half: $0.66 input and $1.98 output per million tokens.
What is DeepSeek V4 Pro 0813’s context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. A single reply can be up to 393,216 tokens.
Does DeepSeek V4 Pro 0813 support prompt caching and batch requests?
Yes, cached input is billed at $0.044 per million tokens (3% of the normal input price). No batch price is published for it.
What are cheaper alternatives to DeepSeek V4 Pro 0813?
With the same essentials (tool calling), the cheapest options are GPT-6 Luna (90% cheaper), Claude Haiku 5.5 (90% cheaper), Qwen3.8 Omni Flash (88% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for DeepSeek V4 Pro 0813?
On OpenRouter it is deepseek/deepseek-v4-pro-0813. In DeepSeek’s own API, use deepseek-v4-pro; DeepSeek lists the model as current. The DeepSeek model ID list has every alias and snapshot. Pass the ID as the model value in each request.
What did DeepSeek V4 Pro 0813 replace?
The previous DeepSeek model in the same line is DeepSeek V4 Pro 0423, first listed on 2026-04-24. Compared with it, DeepSeek V4 Pro 0813’s input price is 532% higher and its output price is 848% higher. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is DeepSeek V4 Pro 0813 open source?
Yes, DeepSeek V4 Pro 0813 has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.