DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813 is the official release of DeepSeek's flagship open model (MIT licence, August 2026): mixture-of-experts with 1.6T parameters and 49B active per token, million-token context. DeepSeek describes greatly enhanced agentic capability, most visible in production environments, and publishes Terminal Bench 2.1 at 87.9 on its card. The model to reach for when a multi-step coding or tool-using agent fails on smaller models. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: deepseek-v4-pro-0813
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="deepseek-v4-pro-0813", 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-pro-0813", "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-pro-0813", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- DeepSeek
- Released
- August 2026
- Licence
- MIT
- Architecture
- mixture of experts · 1.6T parameters, 49B active per token
- Input
- text
- 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 is the April 2026 preview. DeepSeek-V4-Flash-0731 is its official release (284B parameters, 13B active, text only) and the sensible default for code and tool agents at moderate cost.
DeepSeek-V4-Pro-0813 is the flagship: 1.6T parameters with 49B active. DeepSeek recommends allowing up to 384K output tokens at high and max effort — our maximum output for this model is listed under technical details.
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; keep the preview only if you need to reproduce earlier results.
All four are open weights under the MIT licence.
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.
Benchmarks reported by the developer
- Terminal Bench 2.1
- 87.9
- Toolathlon-Verified
- 74.1
- DeepSWE
- 62.7
Figures from the developer's model card, not our measurement. Source: huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813
Settings recommended by the developer
- for agent tasks: temperature 1, top_p 0.95
Technical details
- Context window
- 1M tokens
- Max output
- 65,536 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- DeepSeek
- Streaming
- yes
- Open weights
- deepseek-ai/DeepSeek-V4-Pro-0813
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is DeepSeek-V4-Pro-0813 computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does DeepSeek-V4-Pro-0813 store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the DeepSeek-V4-Pro-0813 context window?
1M tokens, with up to 65,536 tokens of output.
›What does DeepSeek-V4-Pro-0813 cost?
$0.80 per million input tokens and $2.40 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-Pro-0813?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does DeepSeek-V4-Pro-0813 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-Pro-0813 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-Pro-0813?
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-Pro-0813 | DeepSeek | 1.6T / 49B | 1M | MIT | $0.80 |
| DeepSeek-V4.1-Flash | DeepSeek | 552B / 8–16 | 1M | MIT | $0.15 |
| DeepSeek-V4-Flash-0731 | DeepSeek | 284B / 13B | 1.3M | MIT | $0.06 |
| DeepSeek V4 Flash | DeepSeek | 284B / 13B | 1M | MIT | $0.25 |
30 more models behind the same key and the same invoice.
Browse the catalog