AI TOOLS RADAR
Submit
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4 Pro 0813

Source description (English)

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

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
$0.4987
per 1M tokens
Output
$1.4961
per 1M tokens
Cache read
$0.0166
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
1

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-pro-0813","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

24 providers

Checked: September 23, 2026

Live providers on OpenRouter

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

OpenRouter

Baidu

fp8
Context
1.0M
Maximum output
393K
Input
$0.4
Output
$1.1999
Cache read
$0.0127
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
384K
Input
$0.4
Output
$4.3
Cache read
$0.033
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
384K
Input
$0.4
Output
$4.3
Cache read
$0.033
Cache write
Not provided

StreamLake

Not provided
Context
1.0M
Maximum output
384K
Input
$0.462
Output
$1.386
Cache read
$0.0154
Cache write
Not provided

Ionstream

Not provided
Context
1.0M
Maximum output
944K
Input
$0.4992
Output
$2.304
Cache read
$0.0352
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$0.5
Output
$2.9
Cache read
$0.25
Cache write
Not provided

DeepSeek

Not provided
Context
1.0M
Maximum output
384K
Input
$0.66
Output
$1.98
Cache read
$0.022
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.99
Output
$2.97
Cache read
$0.033
Cache write
Not provided

NextBit

fp8
Context
1.0M
Maximum output
944K
Input
$1.056
Output
$3.168
Cache read
$0.035
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$1.056
Output
$3.168
Cache read
$0.0352
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
393K
Input
$1.122
Output
$3.366
Cache read
$0.1122
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
16K
Input
$1.3
Output
$2.6
Cache read
$0.1
Cache write
Not provided

CoreWeave

fp8
Context
1.0M
Maximum output
944K
Input
$1.31
Output
$3.96
Cache read
$0.044
Cache write
Not provided

AtlasCloud

fp8
Context
1.0M
Maximum output
393K
Input
$1.32
Output
$3.96
Cache read
$0.132
Cache write
Not provided

BaseTen

fp4
Context
1.0M
Maximum output
262K
Input
$1.32
Output
$3.96
Cache read
$0.132
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$1.32
Output
$3.96
Cache read
$0.044
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$1.32
Output
$3.96
Cache read
$0.13
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
944K
Input
$1.32
Output
$3.96
Cache read
$0.044
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
393K
Input
$1.32
Output
$3.96
Cache read
$0.044
Cache write
Not provided

BaseTen

fp4
Context
1.0M
Maximum output
262K
Input
$1.32
Output
$3.96
Cache read
$0.132
Cache write
Not provided

Cloudflare

Not provided
Context
1.0M
Maximum output
944K
Input
$1.32
Output
$3.96
Cache read
$0.044
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$1.32
Output
$3.96
Cache read
$0.044
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
393K
Input
$1.45
Output
$4.36
Cache read
$0.15
Cache write
Not provided

Venice

Not provided
Context
1M
Maximum output
33K
Input
$1.65
Output
$4.95
Cache read
$0.165
Cache write
Not provided
deepseek

4 models

All models
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash

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: $0.15Output: $0.6per 1M tokens
View model details →
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: $0.22Output: $0.66per 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: $0.04Output: $0.64per 1M tokens
View model details →