Language model · from 1 credits
Write and analyze with DeepSeek V4 Pro
DeepSeek V4 Pro is the large model of DeepSeek's V4 generation, and one of the best deals in the catalogue: a new compressed-attention architecture gives it a one-million-token context and an efficiency that translates into a price close to the small models. Writing, analysis, code, translation, it holds its own against the established generalists. One limit to know: it reads text only, images connected to the node do not reach it. For a cost-sensitive workflow that refuses to give up quality, it is often the answer, as DeepSeek V3.2 was before it.
A large model at a small model's price
DeepSeek V4 Pro, released on 23 April 2026, owes its price to a new compressed-attention architecture: sixty-six cents per million input tokens, under two dollars per million output, for a one-million-token context and a level that holds its own against the established generalists in writing, analysis, code and translation.
One limit to know before wiring it in: it reads text only. Images connected to the Text node do not reach it; to analyse a visual, take Gemini 3.8 Flash or GPT-5.6 Luna. For a cost-sensitive workflow that refuses to give up quality, it is often the answer.
DeepSeek V4 Pro next to its closest siblings
Figures pulled from the same registry as billing: when a price or a cap changes, this table changes with it.
| DeepSeek V4 Pro | DeepSeek V3.2 | Gemini 3.8 Flash | |
|---|---|---|---|
| Base price | 1 credit(s) / message | 1 credit(s) / message | 1 credit(s) / message |
How to use it on Imaginode
- 1Add a Text node and pick DeepSeek V4 Pro in the selector.
- 2Give your instruction; wire in other texts or images to analyze.
- 3The result feeds your connected Image and Video nodes directly.
Frequently asked questions
Does DeepSeek V4 Pro accept images?
No, text only. On the canvas, leave the Text node's Images port empty with this model, or choose a multimodal one.
How much does a message sent to DeepSeek V4 Pro cost?
Around 1 credit(s) per message, that is $0.01 (1 credit = $0.012). The cost shows before sending, with no separate subscription and no API key to manage: the same credits pay for all 88 models in the catalog.
Do I need a separate subscription to use DeepSeek V4 Pro?
No: DeepSeek V4 Pro is included in Imaginode, with no API key and no account with the provider. A single credit balance covers all 88 models, text, image, video and voice, and also powers the assistant that builds complete workflows.
Can I try DeepSeek V4 Pro for free?
Yes: signing up grants trial credits, no credit card required, and those credits never expire. Enough to test DeepSeek V4 Pro in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use DeepSeek V4 Pro?
No: DeepSeek V4 Pro runs server-side, in the browser, mobile included. Imaginode's node canvas wires its renders to the other models (references, camera, styles) with nothing to install.
Try DeepSeek V4 Pro on a real canvas
88 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
GPT-5 (ChatGPT)