LLM API
DeepSeekText generationReleased September 10, 2026

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash costs $0.15 per 1M input tokens and $0.6 per 1M output tokens on LLM API, with a 1M-token context window.

Pricing

Lowest price among 6 providers, after discounts.

DeepSeek V4.1 Flash prices on LLM API
Input$0.15per 1M tokens
Output$0.6per 1M tokens
Cache read$0.003per 1M tokens
Cache write, 5 minutes$0.15per 1M tokens

Providers

Prices after each provider’s discount; the lowest in bold.

Providers of DeepSeek V4.1 Flash on LLM API
Novita AI$0.3$1.2$0.0061M
Melious$0.354$1.416$0.03541M
Alibaba Cloud$0.15$0.6$0.0151M
DeepSeek$0.15$0.6$0.0031M
Boundless$0.24$0.96$0.00481.05M
Together AI$0.3$1.2$0.0061M

Features

“Some providers”: not every provider of this model supports it.

  • ToolsYes
  • Parallel tool callsNo
  • Image inputYes
  • ReasoningYes

    Levels: low, medium, high, xhigh, max · default medium

  • Prompt cachingYes
  • Structured outputsSome providers
  • JSON modeYes
  • StreamingYes
  • Web searchYes
  • Also acceptsdeepseek-v4.1-flash

Call DeepSeek V4.1 Flash

POST /v1/chat/completionsSet LLMAPI_KEY to your LLM API key.Chat Completions docs

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

More from DeepSeek

All DeepSeek text models

Prices synced .

You've been invited to LLM API

Top up $50 or more and the friend who invited you gets $20 in credits. We pay the $20; your credits stay yours. Referral terms

Sign up