DeepSeek V4.1 Flash
DeepSeek-V4.1-Flash (MIT licence, September 2026) is a multimodal mixture-of-experts model and a different network from V4-Flash: a 552B-parameter backbone that activates 8B per token while reading the prompt and 16B while writing. DeepSeek designed it for input-heavy agentic work — code agents, tool use, agents that look at screens — keeping memory use small even at million-token context. It is served by a third-party inference provider through our partner, not on Heabsy hardware: the same key and the same invoice, but no zero data retention, and the request may be processed outside the EEA.
model id: deepseek-v4.1-flash-cloud
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="deepseek-v4.1-flash-cloud", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v4.1-flash-cloud", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "deepseek-v4.1-flash-cloud", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n
Price list, updated 21 October 2026. No minimum spend, no subscription.
About the model
- Developer
- DeepSeek
- Released
- September 2026
- Licence
- MIT
- Architecture
- mixture of experts · 552B parameters, 8–16B active per token
- Input
- text, images
- Reasoning
- selectable effort
- Languages named by the developer
- none named on the model card
Source: the developer's model card, as of 17 September 2026.
Which DeepSeek model to choose
DeepSeek V4 Flash and V4 Pro are the two sizes of the V4 series. Flash is the efficient one (284B parameters, 13B active, text only) and the sensible default for code and tool agents at moderate cost; Pro is the larger model DeepSeek recommends for pure knowledge and the most complex agentic workflows.
DeepSeek-V4.1-Flash (September 2026) is a different network, not a point release: 552B parameters, 8B active while reading and 16B while writing, and it accepts images. Take it for input-heavy agents.
DeepSeek V3.2 belongs to the earlier V3 line, takes text only and has the shortest context of the four; it is here for workloads already built on it.
All four have open weights. In this catalogue all four are served by partner providers, without zero data retention — for personal or regulated data, use a model on Heabsy hardware.
Licence: what it means for your company
MIT. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
A summary of the licence, not legal advice.
Technical details
- Context window
- 1M tokens
- Max output
- 384,000 tokens
- Throughput limit
- —
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- —
- max_tokens
- 1 … 384000
This model is served by a third-party inference provider through our partner, not on Heabsy hardware. You keep one key and one invoice from an EU company, but there is no zero data retention: the provider handles the request under its own policy, and processing may take place outside the EEA. For personal or regulated data, use a model on Heabsy hardware.
Questions about this model
›Where is DeepSeek V4.1 Flash computed?
At a third-party inference provider that serves this model through our partner, outside our own infrastructure. Where exactly the request is computed is not fixed and may be outside the EEA. The contract and the invoice stay with our EU company.
›Does DeepSeek V4.1 Flash store prompts and completions?
There is no zero-data-retention guarantee for this model: the request goes to a third-party provider, which handles it under its own policy and may keep logs. For personal or regulated data, use a model on Heabsy hardware.
›How large is the DeepSeek V4.1 Flash context window?
1M tokens, with up to 384,000 tokens of output.
›What does DeepSeek V4.1 Flash cost?
$0.28 per million input tokens and $1.04 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on DeepSeek V4.1 Flash?
The catalog does not report a throughput limit for this model.
›Which languages does DeepSeek V4.1 Flash support?
The developer's model card names no languages. Test the model on your own material before relying on it in a particular language.
›Under which licence is DeepSeek V4.1 Flash released?
MIT. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
›Can reasoning be switched off in DeepSeek V4.1 Flash?
The developer lets you choose how much the model reasons; the card does not document turning reasoning off completely.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | 552B / 8–16 | 1M | MIT | $0.28 |
| DeepSeek V4 Flash | DeepSeek | 284B / 13B | 1M | MIT | $0.28 |
| DeepSeek V3.2 | DeepSeek | — | 159K | — | $0.56 |
| DeepSeek V4 Pro | DeepSeek | — | 1M | — | $2.20 |
35 more models behind the same key and the same invoice.
Browse the catalog