deepseek
DeepSeek V4 Flash Vision Exp
Off-peak prices shown. The provider charges 2× during 01:00–04:00 and 06:00–10:00 UTC, Monday–Friday, on the DeepSeek route.
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-flash-vision-exp', messages: [{ role: 'user', content: 'Why is the sky blue?' }], max_tokens: 1024, }),}) const data = await response.json()console.log(data.choices[0].message.content)Text requests and provider peak-hour pricingMiniRouter supports text requests for this model; image input is not supported. Prices shown include MiniRouter's markup. Final charges reflect Vercel's reported usage and any peak-hour surcharge on the DeepSeek route. Pricing details ↗
- Input / 1M
- $0.2264
- Output / 1M
- $0.6791
- Context
- 1M
- Max output
- 1M
Overview
- Model type
- language
- Context window
- 1,048,576
- Maximum output
- 1,048,576
- Input / 1M tokens
- $0.2264
- Output / 1M tokens
- $0.6791
- Released
- 2026-08-21
Prices include the MiniRouter fee. Compatibility snapshot: 2026-08-06. Input: text, image. Output: text.
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-flash-vision-expProviders
| Provider | Priority | Input / 1M | Output / 1M | Parameters | Access |
|---|---|---|---|---|---|
vercel | 1 | $0.2264 | $0.6791 | max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs | MiniRouter balance |