ScaledThought
← All models

DeepSeek

DeepSeek-V4.1-Flash

NewLive · US + CAtextimageMIT

DeepSeek's efficient multimodal update to V4 Flash, MIT-licensed with a 1M-token context window.

Price per 1M tokens

Input

$0.22

Cached input

$0.007

Output

$0.66

Priced per model · Same in US and CA · Free tier included · Pricing

AA Index

39

#6 of 14
open models we serve

Specs

Model id
deepseek-v4-1-flash
Weights released
Sep 10, 2026
Parameters
552B total · 16B active
Architecture
MoE
Context
1M tokens (1,000,000)
Input
text, image
License
MIT
Regions
us, ca

Benchmarks

  • Artificial Analysis Intelligence Index39
  • GPQA Diamond90.9%
  • LiveCodeBench73.3%

Sources: huggingface.co · artificialanalysis.ai · datanorth.ai

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="deepseek-v4-1-flash",
    messages=[{"role": "user", "content": "Hello"}],
)

Opens your agent with the prompt typed. You press Enter.