AI TOOLS RADAR
Submit
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4.1 Flash

Source description (English)

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
384,000 tokens
Architecture
text+image->text
Tokenizer
DeepSeek
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.15
per 1M tokens
Output
$0.6
per 1M tokens
Cache read
$0.003
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
max, high, low
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body 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!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

18 providers

Checked: September 15, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Relace

fp4
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.6
Cache read
$0.015
Cache write
Not provided

DeepSeek

Not provided
Context
1.0M
Maximum output
384K
Input
$0.15
Output
$0.6
Cache read
$0.003
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
131K
Input
$0.2
Output
$0.6
Cache read
$0.006
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$0.22
Output
$0.66
Cache read
$0.007
Cache write
Not provided

Morph

fp8
Context
1.0M
Maximum output
944K
Input
$0.225
Output
$0.9
Cache read
$0.0225
Cache write
Not provided

Io Net

fp8
Context
262K
Maximum output
131K
Input
$0.285
Output
$1.14
Cache read
$0.00285
Cache write
Not provided

Reka

fp4
Context
262K
Maximum output
131K
Input
$0.29
Output
$1.16
Cache read
$0.029
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Modal

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
33K
Input
$0.3
Output
$1.2
Cache read
$0.03
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
393K
Input
$0.345
Output
$1.38
Cache read
$0.0069
Cache write
Not provided

Venice

fp8
Context
1M
Maximum output
131K
Input
$0.375
Output
$1.5
Cache read
$0.0075
Cache write
Not provided
deepseek

4 models

All models
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Context
1.0M
Input
text · image
Output
text
Input: $0.22Output: $0.66per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp (batch)

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Context
1.0M
Input
text · image
Output
text
Input: $0.11Output: $0.33per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $0.9834Output: $2.9502per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813 (batch)

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $0.66Output: $1.98per 1M tokens
View model details →