Deepseek V4.1 Flash 1017 TL0

TL0 Open weights

Open-weight multimodal reasoning and agentic coding with a 1M-token context window

Pricing

Prices for this trust level. Other trust levels are listed below. Prices are per 1M tokens.

Trust levels for this model
Trust Level Region Context Max outputInput / 1MCache / 1MOutput / 1M§203
TL0 US — — 0.28 € 0.31 $ 0.03 € 0.03 $ 1.10 € 1.21 $ —

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.

Other Trust Levels

Prices for the other trust levels available for this model.

Other trust levels for this model
Trust Level Region Context Max outputInput / 1MCache / 1MOutput / 1M§203
TL5 DE 1M 82K 0.25 € 0.28 $ 0.10 € 0.11 $ 1.00 € 1.10 $ §203
TL1 SG — — 0.20 € 0.22 $ 0.018 € 0.020 $ 0.70 € 0.77 $ —

About this model

DeepSeek V4.1 Flash 1017 is DeepSeek's open-weight vision-language Mixture-of-Experts model for complex reasoning, software engineering, and multimodal agent workflows. It retains 552B backbone parameters, with 8B active during input processing and 16B during text generation, plus a 1M-token context window. The model accepts text and images, generates text, and supports tool calling for multi-step tasks. Its October 2026 update improves end-to-end project development, including web applications, games, and code-driven 3D scenes, using reinforcement learning with self-feedback. DeepSeek reports a Terminal-Bench 4.0 improvement from 31.2 to 42.3, alongside faster task completion and shorter outputs. The model weights are released under the MIT license.

API

Model ID deepseek-v4.1-flash-1017-tl0 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-v4.1-flash-1017-tl0",
    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-v4.1-flash-1017-tl0",
  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-v4.1-flash-1017-tl0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently Asked Questions

How much does Deepseek V4.1 Flash 1017 TL0 cost?
Input: 0.28 € per 1M tokens, Cache read: 0.03 € per 1M tokens, Output: 1.10 € per 1M tokens. Prices are exclusive of VAT.
What is the context window of Deepseek V4.1 Flash 1017 TL0?
Deepseek V4.1 Flash 1017 TL0 supports up to — tokens.
Which trust levels are available for Deepseek V4.1 Flash 1017 TL0?
Deepseek V4.1 Flash 1017 TL0 is available at TL5 (Germany Sovereign, DE), TL1 (International Standard, SG), TL0 (Global Unrestricted, US).
Is Deepseek V4.1 Flash 1017 TL0 open weights?
Yes. The model weights are available on Hugging Face under the linked license.
Is Deepseek V4.1 Flash 1017 TL0 available with zero data retention?
Yes. Deepseek V4.1 Flash 1017 TL0 is served at TL0 (Global Unrestricted) with zero data retention and no model training.
How do I use Deepseek V4.1 Flash 1017 TL0 with the OpenAI SDK?
Use the model ID deepseek-v4.1-flash-1017-tl0 with the OpenAI-compatible endpoint at https://api.aki.io/v1.

Start Building with Deepseek V4.1 Flash 1017 TL0