Deepseek V4 Pro 0813 TL1

TL1 Open weights

Open-weight agentic coding and reasoning with 1M context and 1.65T parameters

Pricing

Prices for this trust level. Prices are per 1M tokens.

Trust levels for this model
Trust Level Region Context Max outputInput / 1MCache / 1MOutput / 1M§203
TL1 SG — — 1.00 € 1.10 $ 0.10 € 0.11 $ 2.00 € 2.20 $ —

USD prices are converted from EUR at the ECB reference rate of 1 EUR = 1.1014 USD (2026-11-16). EUR prices are authoritative.

Prices as of 16.11.2026.

About this model

DeepSeek V4 Pro 0813 is DeepSeek's August 2026 open-weight release of its flagship text-only reasoning model. Its sparse Mixture-of-Experts architecture combines 1.65T total parameters with 49B active per token and a 1M-token context window. Hybrid Compressed Sparse Attention and Heavily Compressed Attention support efficient long-context processing, while the attached DSpark speculative-decoding module accelerates inference. The release improves agentic software engineering, repository-level coding, multi-step tool use, and workflow automation. Users can select low, high, or max reasoning effort according to task complexity. In DeepSeek's own evaluations, Terminal-Bench 2.1 rose to 87.9. The model accepts and generates text, supports tool calling, and is released under the MIT license.

API

Model ID deepseek-v4-pro-0813-tl1 OpenAI compatibleAnthropic compatible

Base URL https://api.aki.io/v1

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AKI_API_KEY",
    base_url="https://api.aki.io/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-pro-0813-tl1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_AKI_API_KEY",
  baseURL: "https://api.aki.io/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro-0813-tl1",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
curl https://api.aki.io/v1/chat/completions \
  -H "Authorization: Bearer $AKI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro-0813-tl1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently Asked Questions

How much does Deepseek V4 Pro 0813 TL1 cost?
Input: 1.00 € per 1M tokens, Cache read: 0.10 € per 1M tokens, Output: 2.00 € per 1M tokens. Prices are exclusive of VAT.
What is the context window of Deepseek V4 Pro 0813 TL1?
Deepseek V4 Pro 0813 TL1 supports up to — tokens.
Which trust levels are available for Deepseek V4 Pro 0813 TL1?
Deepseek V4 Pro 0813 TL1 is available at TL1 (International Standard, SG).
Is Deepseek V4 Pro 0813 TL1 open weights?
Yes. The model weights are available on Hugging Face under the linked license.
Is Deepseek V4 Pro 0813 TL1 available with zero data retention?
Yes. Deepseek V4 Pro 0813 TL1 is served at TL1 (International Standard) with zero data retention and no model training.
How do I use Deepseek V4 Pro 0813 TL1 with the OpenAI SDK?
Use the model ID deepseek-v4-pro-0813-tl1 with the OpenAI-compatible endpoint at https://api.aki.io/v1.

Start Building with Deepseek V4 Pro 0813 TL1