AI TOOLS RADAR
Submit
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0731

Source description (English)

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....

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,310,720 tokens
Maximum output
943,718 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
$0.04
per 1M tokens
Output
$0.64
per 1M tokens
Cache read
$0.016
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-flash-0731","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Available providers

29 providers

Checked: September 22, 2026

Live providers on OpenRouter

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

OpenRouter

OpenInference

fp8
Context
1.0M
Maximum output
944K
Input
$0.03
Output
$1
Cache read
$0.012
Cache write
Not provided

Relace

fp4
Context
1.0M
Maximum output
944K
Input
$0.04
Output
$0.64
Cache read
$0.016
Cache write
Not provided

StreamLake

fp8
Context
1.0M
Maximum output
384K
Input
$0.0528
Output
$0.1584
Cache read
$0.00168
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
384K
Input
$0.06
Output
$0.18
Cache read
$0.015
Cache write
Not provided

Inceptron

fp4
Context
1.0M
Maximum output
944K
Input
$0.06
Output
$0.3
Cache read
$0.04
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
944K
Input
$0.0741
Output
$0.342
Cache read
$0.0228
Cache write
Not provided

Reka

fp4
Context
262K
Maximum output
131K
Input
$0.088
Output
$0.528
Cache read
$0.0056
Cache write
Not provided

Makora

Not provided
Context
1M
Maximum output
384K
Input
$0.09
Output
$0.195
Cache read
$0.0196
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$0.1
Output
$0.25
Cache read
$0.05
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
944K
Input
$0.119
Output
$0.238
Cache read
$0.0238
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
384K
Input
$0.13
Output
$0.26
Cache read
$0.028
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
384K
Input
$0.13
Output
$0.26
Cache read
$0.028
Cache write
Not provided

CoreWeave

fp8
Context
262K
Maximum output
236K
Input
$0.13
Output
$0.28
Cache read
$0.07
Cache write
Not provided

Nebius

fp8
Context
1.0M
Maximum output
922K
Input
$0.14
Output
$0.28
Cache read
Not provided
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$0.14
Output
$0.28
Cache read
$0.03
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$0.14
Output
$0.28
Cache read
$0.05
Cache write
Not provided

Morph

Not provided
Context
1.0M
Maximum output
944K
Input
$0.142
Output
$0.3996
Cache read
$0.0359
Cache write
Not provided

Venice

Not provided
Context
1M
Maximum output
33K
Input
$0.175
Output
$0.35
Cache read
$0.035
Cache write
Not provided

Mancer 2

fp8
Context
1.0M
Maximum output
944K
Input
$0.2
Output
$0.6
Cache read
Not provided
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

SiliconFlow

fp8
Context
1.0M
Maximum output
393K
Input
$0.22
Output
$0.66
Cache read
$0.028
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.286
Output
$0.858
Cache read
$0.0091
Cache write
Not provided

NextBit

fp8
Context
1.0M
Maximum output
944K
Input
$0.352
Output
$1.056
Cache read
$0.012
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
393K
Input
$0.352
Output
$1.056
Cache read
$0.0352
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.4092
Output
$1.2276
Cache read
$0.026
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
393K
Input
$0.44
Output
$1.32
Cache read
$0.028
Cache write
Not provided

Baidu

fp8
Context
1.0M
Maximum output
131K
Input
$0.44
Output
$1.32
Cache read
$0.014
Cache write
Not provided

AtlasCloud

fp4
Context
1.0M
Maximum output
393K
Input
$0.44
Output
$1.32
Cache read
$0.028
Cache write
Not provided

Cloudflare

Not provided
Context
1.3M
Maximum output
1.2M
Input
$0.44
Output
$1.32
Cache read
$0.014
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 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: $0.4987Output: $1.4961per 1M tokens
View model details →