AI TOOLS RADAR
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
943,718 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
$0.3
per 1M tokens
Output
$1.2
per 1M tokens
Cache read
$0.006
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

31 providers

Checked: September 29, 2026

Live providers on OpenRouter

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

OpenRouter

Relace

Not provided
Context
1.0M
Maximum output
944K
Input
$0.02
Output
$0.6
Cache read
$0.01
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$0.0449
Output
$0.7
Cache read
$0.0359
Cache write
Not provided

InferenceNet

Not provided
Context
1.0M
Maximum output
384K
Input
$0.06
Output
$0.39
Cache read
$0.02
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
384K
Input
$0.08
Output
$0.4
Cache read
$0.01
Cache write
Not provided

Morph

fp8
Context
1.0M
Maximum output
944K
Input
$0.0805
Output
$0.51
Cache read
$0.0027
Cache write
Not provided

OpenInference

fp4
Context
1.0M
Maximum output
944K
Input
$0.1
Output
$0.5
Cache read
$0.01
Cache write
Not provided

AtlasCloud

fp8
Context
1.0M
Maximum output
393K
Input
$0.114
Output
$0.456
Cache read
$0.0114
Cache write
Not provided

DekaLLM

Not provided
Context
1.0M
Maximum output
944K
Input
$0.12
Output
$0.4
Cache read
$0.005
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
131K
Input
$0.14
Output
$0.42
Cache read
$0.0042
Cache write
Not provided

StreamLake

fp8
Context
1.0M
Maximum output
384K
Input
$0.1785
Output
$0.714
Cache read
$0.00357
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.18
Output
$0.72
Cache read
$0.0036
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.195
Output
$0.78
Cache read
$0.0039
Cache write
Not provided

CoreWeave

fp8
Context
1.0M
Maximum output
944K
Input
$0.2
Output
$0.65
Cache read
$0.03
Cache write
Not provided

NextBit

fp8
Context
1.0M
Maximum output
944K
Input
$0.21
Output
$0.84
Cache read
$0.004
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

Krea

fp8
Context
1.0M
Maximum output
944K
Input
$0.225
Output
$0.9
Cache read
$0.006
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
393K
Input
$0.276
Output
$1.104
Cache read
$0.00552
Cache write
Not provided

Ionstream

Not provided
Context
1.0M
Maximum output
944K
Input
$0.28
Output
$1.15
Cache read
$0.005
Cache write
Not provided

Baidu

fp8
Context
1.0M
Maximum output
393K
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

Makora

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

DigitalOcean

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

BaseTen

fp8
Context
1.0M
Maximum output
33K
Input
$0.3
Output
$1.2
Cache read
$0.007
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

DeepSeek

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

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$0.45
Output
$1.8
Cache read
$0.009
Cache write
Not provided
deepseek

4 models

All models
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash (batch)

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...

Context
1.0M
Input
text · image
Output
text
Input: $0.112Output: $0.336per 1M tokens
View model details →
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: $0.2156Output: $0.6468per 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: $0.3949Output: $4.2per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Context
1.3M
Input
text
Output
text
Input: $0.018Output: $0.32per 1M tokens
View model details →