DeepseekTool use

DeepSeek V4 Flash 0731 pricing

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. This page tracks 13 listings in total. Highlighted lows are $0.030 per million input and $0.180 per million output (see table for which seller matches each).

1.0M context·13 providers·verified Sep 25, 2026
Best input$0.030per 1M tokens · Openrouter
Best output$0.180per 1M tokens · DeepInfra

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 13 offers are listed for DeepSeek V4 Flash 0731. Best input in this view: Openrouter.

AC
Alibaba Cloud
Input / 1M
$0.200
Output / 1M
$0.400
Cached in: $0.040
A
Azure
Input / 1M
$0.440
Output / 1M
$1.32
Cached in: $0.014
B
Baseten
Input / 1M
$0.130
Output / 1M
$0.260
Cached in: $0.028
D
DeepInfra
Input / 1M
$0.080
Output / 1M
$0.180
Cached in: $0.016
FA
Fireworks AI
Input / 1M
$0.220
Output / 1M
$0.660
Cached in: $0.0070
N
Nebius
Input / 1M
$0.140
Output / 1M
$0.280
N
Novita
Input / 1M
$0.440
Output / 1M
$1.32
Cached in: $0.028
O
Openrouter
Input / 1M
$0.030
Output / 1M
$0.320
QA
Qwen Ai Platform
Input / 1M
$0.200
Output / 1M
$0.400
Cached in: $0.040
Q
Qwencloud
Input / 1M
$0.200
Output / 1M
$0.400
Cached in: $0.040
S
Scaleway
Input / 1M
$0.400
Output / 1M
$0.800
Cached in: $0.080
TA
Together AI
Input / 1M
$0.140
Output / 1M
$0.280
Cached in: $0.030
W
Wandb
Input / 1M
$0.130
Output / 1M
$0.280
Cached in: $0.070

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how DeepSeek V4 Flash 0731 cost scales with traffic.

Provider

In: $0.200/M·Out: $0.400/M·Cache: $0.040/M

0.020000¢ / req

0.020000¢ / req

Daily
$4.00
Monthly
$120
Annual
$1.5K

Model specifications

Context length, caps, and capability flags for DeepSeek V4 Flash 0731. Values follow the main provider (Deepseek) record in our index.

Context window
1,048,576 tokens
Max output
384,000 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
Yes
Released
Jul 2026
Primary provider
Deepseek
Model family
N/A

Compare DeepSeek V4 Flash 0731

These links open full side by side pages for DeepSeek V4 Flash 0731. We picked pairs that people often shop together. 6 ready to open.

Locked

Compare with

Pick a model on both sides.

Popular DeepSeek V4 Flash 0731 comparisons

Frequently asked questions

Quick frequently asked items for DeepSeek V4 Flash 0731 pricing and limits. The short model note from our index: 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.

Yes. DeepSeek V4 Flash 0731 is available on Alibaba Cloud, Azure, Baseten, DeepInfra, Fireworks AI, Nebius, Novita, Openrouter, Qwen Ai Platform, Qwencloud, Scaleway, Together AI, Wandb.

Related models

Models close to DeepSeek V4 Flash 0731 by family, provider, and context window — each with live pricing in our catalog.