Loading model…正在加载模型详情…
Loading model…正在加载模型详情…
Chat with DeepSeek V4 through a shared workspace for the Flash, Pro and legacy Flash model IDs.
Use it inCodex CLI setup
DeepSeek V4 is a language model from DeepSeek. Ask questions, supply relevant text and continue the discussion through follow-up messages in this workspace. Select V4 Flash, V4 Pro or the legacy DeepSeek Flash ID from the variant row.
Use the exact model ID shown in the specifications table when integrating the model. The API section lists the request formats supported for it.
What DeepSeek V4 is built for.
Ask a question, supply relevant context and refine the response through follow-up messages.
Use the model ID and the request formats shown in the API section to add text conversations to your application.
The chat workspace accepts text messages; API formats and available controls are listed below for the selected variant.
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| DeepSeek Flash | deepseek-flash | Chat and text generation | OpenAI Chat Completions API | Context window: Not stated on this page | $0.23 input / $0.90 output per 1M tokens |
| DeepSeek V4 Flash | deepseek-v4-flash | Chat and text generation | OpenAI Chat Completions API | Context window: Not stated on this page | $0.33 input / $0.99 output per 1M tokens |
| DeepSeek V4 Pro | deepseek-v4-pro | Chat and text generation | OpenAI Chat Completions API | Context window: Not stated on this page | $0.99 input / $2.97 output per 1M tokens |
Priced per token. Input and output are billed separately.
| Usage | DeepSeek list price | UniRoute |
|---|---|---|
| Input | $1.32 | $0.99 |
| Output | $3.96 | $2.97 |
| Cache read | $0.04 | — |
Pricing source: api-docs.deepseek.com · 2026-11-07
Rounded to the cent; the live quote in the workspace shows the exact amount. Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
Call DeepSeek V4 through OpenAI Chat Completions API.
curl 'https://api.uniroute.app/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "deepseek-v4-pro", "messages": [ { "role": "user", "content": "Hello" } ], "stream": false}'| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
messages | Body | The conversation as a list of role and content messages. |
stream | Body | Set to true to receive the response as a stream. |
Typical ways to put DeepSeek V4 to work.
Provide background information and ask focused questions, then check the response against your source material.
Share a draft and explain the intended audience so the model can suggest clearer wording.
Connect the documented API format to a conversation flow in your own application.
Common questions about DeepSeek V4.
DeepSeek V4 is a language model from DeepSeek. Ask questions, supply relevant text and continue the discussion through follow-up messages in this workspace. Select V4 Flash, V4 Pro or the legacy DeepSeek Flash ID from the variant row.
The variant selector lists the callable model IDs on UniRoute. Unavailable operations are omitted, and the specifications table shows the available options.
From $0.99 input / $2.97 output per 1M tokens. The Pricing section lists the available rates for the selected variant and settings, with prices updated 2026-11-08.
Create a UniRoute API key and use a request format listed in the API section with the selected model ID.
The chat workspace accepts text messages. The API section lists the request formats and parameters for the selected variant.
No. Requests are paid from your wallet balance. You can read this page and review the prices without paying, and you need an account with funds to send a message.