AI TOOLS RADAR
Explore
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0423

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. $0.0679 per million input tokens, $0.168 per million output tokens. 1,048,576 token context window. Higher uptime with 17 providers. Includes independent benchmarks from Artificial Analysis.

View source on OpenRouter Hugging Face
Overview

Model specifications

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

Complete pricing

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

Input
$0.0679
/M tokens
Output
$0.168
/M tokens
Cache read
$0.0168
/M tokens
API

Model configuration

Reasoning

Moderated
No
Default parameters
high
Capabilities
xhigh, high
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No · xhigh · high

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Available providers

17 providers

Live providers on OpenRouter

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

OpenRouter

DigitalOcean

unknown
Context
1.0M
Maximum output
944K
Input
$0.068
Output
$0.168
Cache read
$0.017
Cache write
Not provided

StreamLake

fp8
Context
1.0M
Maximum output
384K
Input
$0.089
Output
$0.177
Cache read
$0.018
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
66K
Input
$0.090
Output
$0.180
Cache read
$0.018
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.112
Output
$0.224
Cache read
$0.022
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
393K
Input
$0.130
Output
$0.280
Cache read
$0.028
Cache write
Not provided

Alibaba

fp8
Context
1M
Maximum output
393K
Input
$0.134
Output
$0.268
Cache read
$0.027
Cache write
Not provided

Venice

unknown
Context
1M
Maximum output
33K
Input
$0.138
Output
$0.275
Cache read
$0.028
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.140
Output
$0.280
Cache read
$0.028
Cache write
Not provided

NextBit

fp8
Context
1.0M
Maximum output
944K
Input
$0.140
Output
$0.280
Cache read
$0.028
Cache write
Not provided

AtlasCloud

fp4
Context
1.0M
Maximum output
393K
Input
$0.140
Output
$0.280
Cache read
$0.028
Cache write
Not provided

Baidu

fp8
Context
1.0M
Maximum output
131K
Input
$0.140
Output
$0.280
Cache read
$0.028
Cache write
Not provided

CoreWeave

fp8
Context
1.0M
Maximum output
944K
Input
$0.140
Output
$0.280
Cache read
$0.070
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$0.140
Output
$0.280
Cache read
$0.070
Cache write
Not provided

Mancer 2

fp8
Context
1.0M
Maximum output
944K
Input
$0.180
Output
$0.500
Cache read
Not provided
Cache write
Not provided

Phala

unknown
Context
1.0M
Maximum output
393K
Input
$0.200
Output
$0.400
Cache read
$0.070
Cache write
Not provided

Azure

unknown
Context
1.0M
Maximum output
384K
Input
$0.210
Output
$0.560
Cache read
$0.031
Cache write
Not provided

Cloudflare

unknown
Context
384K
Maximum output
346K
Input
$0.440
Output
$1.32
Cache read
$0.014
Cache write
Not provided
deepseek

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: $0.440Output: $1.32per 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: $1.32Output: $3.96per 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: $1.32Output: $3.96per 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: $0.065Output: $0.180per 1M tokens
View model details →