AI model · DeepSeek
DeepSeek: DeepSeek V4 Pro 0813 available
deepseek/deepseek-v4-pro-0813
DeepSeek: DeepSeek V4 Pro 0813 costs US$ 0.111 per million input tokens and US$ 4.44 per million output tokens (OpenRouter reference price, verified 2026-11-12).
| Input price (per 1M tokens) | US$ 0.111 |
|---|---|
| Output price (per 1M tokens) | US$ 4.44 |
| Typical request (2,000 tokens in, 500 out) | US$ 0.00244 |
| Context window | 1,048,576 |
| Max output tokens | 943,718 |
| Announced retirement date | none |
| Knowledge cutoff | — |
| Last verified | 2026-11-12 17:41:12 UTC |
Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.
Frequently asked questions
How much does DeepSeek: DeepSeek V4 Pro 0813 cost?
DeepSeek: DeepSeek V4 Pro 0813 costs US$ 0.111 per million input tokens and US$ 4.44 per million output tokens (OpenRouter reference price, verified 2026-11-12).
What is the context window of DeepSeek: DeepSeek V4 Pro 0813?
DeepSeek: DeepSeek V4 Pro 0813 accepts up to 1,048,576 tokens of context.
Is DeepSeek: DeepSeek V4 Pro 0813 being retired?
No retirement date has been announced for DeepSeek: DeepSeek V4 Pro 0813 (checked 2026-11-12).
Other DeepSeek models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| deepseek/deepseek-v4.1-flash-1017 | US$ 0.15 | US$ 0.6 | 1,048,576 |
| deepseek/deepseek-v4.1-flash-1017:batch | US$ 0.05 | US$ 0.15 | 1,048,576 |
| deepseek/deepseek-v4.1-flash | US$ 0.3 | US$ 1.20 | 1,048,576 |
| deepseek/deepseek-v4.1-flash:batch | US$ 0.112 | US$ 0.336 | 1,048,576 |
| deepseek/deepseek-v4-flash-vision-exp | US$ 0.44 | US$ 1.32 | 1,048,576 |
| deepseek/deepseek-v4-flash-0731 | US$ 0.0434 | US$ 0.3 | 1,048,576 |
| deepseek/deepseek-v4-flash-0731:batch | US$ 0.048 | US$ 0.144 | 1,048,576 |
| deepseek/deepseek-v4-pro | US$ 0.892 | US$ 1.78 | 1,048,576 |
| deepseek/deepseek-v4-flash | US$ 0.09 | US$ 0.18 | 1,048,576 |
| deepseek/deepseek-v3.2 | US$ 0.26 | US$ 0.38 | 163,840 |
| deepseek/deepseek-v3.2-exp | US$ 0.27 | US$ 0.41 | 163,840 |
| deepseek/deepseek-v3.1-terminus | US$ 0.27 | US$ 1.00 | 163,840 |
| deepseek/deepseek-chat-v3.1 | US$ 0.25 | US$ 0.95 | 163,840 |
| deepseek/deepseek-r1-0528 | US$ 0.5 | US$ 2.15 | 163,840 |
| deepseek/deepseek-chat-v3-0324 | US$ 0.29 | US$ 1.14 | 163,840 |
| deepseek/deepseek-chat | US$ 0.32 | US$ 0.89 | 163,840 |
Give your AI agent these facts
Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.
claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp
Add to CursorAdd to VS Code★ Star on GitHub
Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests
For agents
GET https://vigia.coredls.cloud/v1/models/deepseek/deepseek-v4-pro-0813