DeepSeek V4.1 Flash
Where it stands
Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.
About this model
DeepSeek V4.1 Flash is an AI model from DeepSeek, made available through the API on September 10, 2026. It can read up to 1,048,576 tokens in one request, roughly 1,966 pages of text, and write up to 943,718 tokens in a single answer. Besides text, it accepts images as input.
Through the API it costs $0.30 per million input tokens and $1.20 per million output tokens. Its pricing sits in the middle of the market.
It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (deepseek-ai/DeepSeek-V4.1-Flash), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →Where to use it
Companies that serve this model through an API: 33. Prices per million tokens, cheapest first.
| Provider | Inputi | Outputi | Contexti | Uptime (24 h)i |
|---|---|---|---|---|
Sail ResearchCheapestfp4 | $0.08 | $0.40 | 1M | 95.3% |
InferenceNet | $0.069 | $0.45 | 1M | 98.8% |
Wafer | $0.08 | $0.44 | 1M | 99.8% |
DekaLLM | $0.12 | $0.40 | 1M | 97.1% |
OpenInferencefp4 | $0.03 | $0.50 | 1M | 99.1% |
DeepInfrafp8 | $0.14 | $0.42 | 1M | 99.9% |
AtlasCloudfp8 | $0.11 | $0.46 | 1M | 99.9% |
Morphfp8 | $0.081 | $0.51 | 1M | 96.4% |
Relace | $0.02 | $0.60 | 1M | 99.9% |
DeepSeekOfficial | $0.15 | $0.60 | 1M | 100.0% |
StreamLakefp8 | $0.17 | $0.66 | 1M | 99.6% |
CoreWeavefp8 | $0.20 | $0.65 | 1M | 99.0% |
Fireworks | $0.22 | $0.66 | 1M | 99.0% |
GMICloudfp8 | $0.18 | $0.72 | 1M | 99.7% |
Novitafp8 | $0.20 | $0.78 | 1M | 99.9% |
NextBitfp8 | $0.21 | $0.84 | 1M | 99.8% |
Phala | $0.21 | $0.84 | 1M | 99.7% |
Kreafp8 | $0.23 | $0.90 | 1M | 99.1% |
Ionstream | $0.15 | $1 | 1M | 95.4% |
Io Netfp8 | $0.25 | $1 | 1M | 99.8% |
Baidufp8 | $0.30 | $1.20 | 1M | 99.4% |
BaseTenfp8 | $0.30 | $1.20 | 1M | 99.2% |
Makorafp8 | $0.30 | $1.20 | 1M | 99.8% |
DigitalOcean | $0.30 | $1.20 | 1M | 99.6% |
Alibaba | $0.30 | $1.20 | 1M | 99.7% |
Together | $0.30 | $1.20 | 1M | 99.9% |
SiliconFlowfp8 | $0.30 | $1.20 | 1M | 99.8% |
Modal | $0.30 | $1.20 | 1M | 99.8% |
BaseTenfp8 | $0.30 | $1.20 | 1M | 98.6% |
Parasailfp8 | $0.30 | $1.20 | 1M | 99.3% |
Venicefp8 | $0.38 | $1.50 | 1M | 95.2% |
Fireworks | $0.45 | $1.80 | 1M | 99.9% |
BaseTenfp32 | $0.60 | $2.40 | 1M | 99.9% |
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call DeepSeek V4.1 Flash through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek/deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="deepseek/deepseek-v4.1-flash",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "deepseek/deepseek-v4.1-flash",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0.51
- Summarise a 100-page document$0.016
- An app with 10,000 requests a day for a month$234
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
Command A+Cohere | $0.30 | $1.50 | 192K | Compare with ⇄ |
GLM 5.3 FlashXZ.ai (Zhipu) | $0.37 | $1.25 | 1M | Compare with ⇄ |
Gemini 3.5 Flash LiteGoogle DeepMind | $0.30 | $2.50 | 1M | Compare with ⇄ |
LongCat 2.0Meituan | $0.30 | $1.20 | 1M | Compare with ⇄ |
MiniMax M3MiniMax | $0.30 | $1.20 | 1M | Compare with ⇄ |
Qwen3.5 Plus 2026-04-20Alibaba Qwen | $0.30 | $1.80 | 1M | Compare with ⇄ |
News about DeepSeek
See all →Frequently asked questions
- How much does DeepSeek V4.1 Flash cost?
- DeepSeek V4.1 Flash costs $0.30 per million input tokens and $1.20 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.51.
- What is the context window of DeepSeek V4.1 Flash?
- DeepSeek V4.1 Flash can read up to 1,048,576 tokens in one request, about 1,966 pages of text. It can write up to 943,718 tokens in a single answer.
- Is DeepSeek V4.1 Flash open source?
- Yes. Its weights are published (deepseek-ai/DeepSeek-V4.1-Flash), so you can download it and run it on your own hardware, or use it through one of 33 API providers.
- Who makes DeepSeek V4.1 Flash?
- DeepSeek V4.1 Flash is made by DeepSeek. It became available through the API on September 10, 2026.
- How good is DeepSeek V4.1 Flash?
- DeepSeek V4.1 Flash has an overall index of 155.0 in Epoch AI’s independent tests, ranking #27 of 136 models we track.
- Can DeepSeek V4.1 Flash read images?
- Yes. Besides text, it accepts images as input.
- What are the alternatives to DeepSeek V4.1 Flash?
- Models with a similar price from other companies include Command A+, GLM 5.3 FlashX and Gemini 3.5 Flash Lite. You can compare them side by side on this page.