deepseek
DeepSeek V4 Pro 0813
Off-peak prices shown. The provider charges 2× during 00:00–14:00 UTC every day.
Replaces DeepSeek V4 Pro: input $1.386 → $0.693 per 1M (-50%), output $4.158 → $2.079 per 1M (-50%), context 1M → 1M, max output 1M → 384K.
Use an endpoint supported by this model.
Get a key for this setup →const response = await fetch('https://api.minirouter.sh/v1/chat/completions', { method: 'POST', headers: { Authorization: `Bearer ${process.env.MINIROUTER_KEY}`, 'Content-Type': 'application/json', }, body: JSON.stringify({ model: 'deepseek/deepseek-v4-pro-0813', messages: [{ role: 'user', content: 'Why is the sky blue?' }], max_tokens: 1024, }),}) const data = await response.json()console.log(data.choices[0].message.content)Provider peak-hour pricingPrices shown include MiniRouter's markup. Final charges reflect Vercel's reported usage and any peak-hour surcharge. Pricing details ↗
- Input / 1M
- $0.693
- Output / 1M
- $2.079
- Context
- 1M
- Max output
- 384K
Overview
- Model type
- language
- Context window
- 1,000,000
- Maximum output
- 384,000
- Input / 1M tokens
- $0.693
- Output / 1M tokens
- $2.079
- Released
- 2026-08-12
Prices include the MiniRouter fee. Compatibility snapshot: 2026-08-06. Input: text. Output: text. Compare text-model alternatives or estimate token costs for your workload.
Endpoints
/v1/chat/completions/v1/messages/v1/responsesJSON Schema and JSON mode enforced on verified providers. How it works
Captured parameters: max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs.
API
https://api.minirouter.sh/v1deepseek/deepseek-v4-pro-0813Providers
| Provider | Priority | Input / 1M | Output / 1M | Parameters | Access |
|---|---|---|---|---|---|
vercel | 1 | $0.693 | $2.079 | max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs | MiniRouter balance |