Hoodgen
Sign in
DeepseekFastReleased 31 July 2026

DeepSeek V4 Flash 0731 pricing, context and benchmark

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Chat with DeepSeek V4 Flash 0731
1.05M
Input context
944K
Output context
$0.043
Official input
$0.3
Official output
n/a
AA index
01 · Model Overview

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

ModelDeepSeek V4 Flash 0731
Model IDdeepseek/deepseek-v4-flash-0731
ProviderDeepseek
Release date31 July 2026
StatusGenerally available
Input context1,048,576 tokens
Output context943,718 tokens
Official input pricing$0.043 per 1M tokens
Official output pricing$0.3 per 1M tokens
Cache read pricingNot published
Market input pricing$0.043 per 1M (cheapest route)
Market output pricing$0.3 per 1M (cheapest route)
Input modalitiestext
Output modalitiestext
Reasoning controlNot exposed
Tool supportText generation only
TokenizerDeepSeek
Provider routes8 endpoints
Artificial Analysis indexNot published
SpeedNot published
Knowledge cutoffNot publicly stated

Input and output support

ModalityInputOutputBilled at
Text✓ yes✓ yes$0.043 in
Imagenononot supported
Audionononot supported
Videonononot supported
File (PDF)nononot supported
02 · Overview

What is 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....

DeepSeek V4 Flash 0731 carries a 1.05M token window, uses the DeepSeek tokenizer and is served by Deepseek. On Hoodgen it sits in the Fast tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

03 · Release

Release and what changed from the previous version

Released31 July 2026
PropertyDeepSeek V4 Pro 0423DeepSeek V4 Flash 0731Change
Released20262026Same release window
Context1.05M1.05MUnchanged
Max output944K944KUnchanged
Input price$0.9$0.043Cheaper
Output price$1.5$0.3Cheaper
Input modalitiestexttextUnchanged
AA indexn/an/aNewer benchmark run
07 · Use cases

What can you do with DeepSeek V4 Flash 0731?

High volume drafts
Captions, titles, product blurbs and rewrite passes where cost per call dominates.
Inline assistants
Autocomplete, quick replies and menu helpers that must answer inside a second.
Batch classification
Tagging, routing and extraction across thousands of short inputs.
Cheap agent loops
Tool calling loops that do not need frontier grade reasoning.
09 · Pricing

DeepSeek V4 Flash 0731 pricing

Official pricing

List price
$0.043 / 1M in
$0.3 / 1M out
  • 1.05M context
  • text input
Cheapest route
$0.043 / 1M in
$0.3 / 1M out
  • 8 routes on OpenRouter
  • What Hoodgen routes to first
  • Same model, lower bill

Market pricing, every route

ProviderTierInputOutputCache readUptime 24h
Waferstandard$0.043$0.3$0.035100.0%
Baidustandard$0.06$0.18$0.001991.6%
DeepInfrastandard$0.06$0.18$0.015100.0%
Relacestandard$0.07$0.14$0.014100.0%
DigitalOceanstandard$0.119$0.238$0.02499.9%
BaseTenstandard$0.13$0.26$0.028100.0%
BaseTenstandard$0.13$0.26$0.028100.0%
Venicestandard$0.13$0.26$0.028100.0%

API pricing and cost calculator

RatePer callTotalCredits
Cheapest route$0.0012$0.61579
List price$0.0013$0.66627
10 · Developers

API and developer information

Model IDdeepseek/deepseek-v4-flash-0731
Endpointhttps://openrouter.ai/api/v1/chat/completions
Parametersprompt and max_tokens
StreamingYes, server sent events
Modality stringtext->text
Max prompt tokens1,048,576
Max completion tokens943,718
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-0731",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'
11 · Limitations

Model limitations

Text only outputIt cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals.
Output cap943,718 tokens per request. Long deliverables have to be chunked.
Benchmarks not publishedArtificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoffThe provider does not state a fixed cutoff for every release. Verify very recent events against search.
Depth ceilingFast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning.
12 · Comparison

DeepSeek V4 Flash 0731 vs other Deepseek models

ModelContextInput /1MOutput /1MAA indexReleased
DeepSeek V4 Flash 07311.05M$0.043$0.3n/a2026
DeepSeek V4 Pro 04231.05M$0.9$1.5n/a2026
R1 0528164K$0.5$2.15n/a2025
DeepSeek V3.1164K$0.25$0.95n/a2025
V4 Flash Vision Exp1.05M$0.216$0.647n/a2026
DeepSeek V4 Pro 08131.05M$0.1$8n/a2026
13 · Privacy

Privacy and data policy

  • On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
  • Requests route through OpenRouter to Deepseek and are covered by that provider's API terms.
  • Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ

DeepSeek V4 Flash 0731 questions, answered

DeepSeek V4 Flash 0731 is a fast model from Deepseek, released 31 July 2026. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
✦

Start chatting with DeepSeek V4 Flash 0731

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.

Open Chat, it is freeCompare all models