DeepSeek V4 Flash 0731

DeepSeek · On OpenRouter since July 31, 2026 · Pinned version id: deepseek/deepseek-v4-flash-20260731

Price

$0.09

mixed / 1M tokens

Mixed price per 1M tokens: 3 input tokens to 1 output token.

in $0.06 · out $0.18 · Cached input $0.015

via DeepInfra

Price disputed

Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.

US dollars per million tokens, converted to your currency at the NBP rate.

Tasks, with the evidence

Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.

Writing code Top 25%

Measured by a third party

Coding Index: 69.1 · Rank 15 of 86, among scored models · Top 25% · Artificial Analysis, read November 18, 2026

Code: 1,212 · Rank 58 of 122, among scored models · Design Arena, read November 21, 2026

Agents that use tools Top 25%

Measured by a third party

Agentic Index: 41.0 · Rank 9 of 64, among scored models · Artificial Analysis, read November 18, 2026

Websites and apps

Measured by a third party

Websites: 1,225 · Rank 57 of 127, among scored models · Design Arena, read November 21, 2026

UI components: 1,221 · Rank 53 of 118, among scored models · Design Arena, read November 21, 2026

Games and 3D

Measured by a third party

Game development: 1,187 · Rank 57 of 121, among scored models · Design Arena, read November 21, 2026

3D scenes: 1,175 · Rank 54 of 114, among scored models · Design Arena, read November 21, 2026

Charts and graphics

Measured by a third party

Data visualization: 1,166 · Rank 68 of 112, among scored models · Design Arena, read November 21, 2026

SVG graphics: 1,164 · Rank 44 of 84, among scored models · Design Arena, read November 21, 2026

ASCII art: 1,083 · Rank 62 of 68, among scored models · Design Arena, read November 21, 2026

Long documents

Declared, not measured

Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.

Ranks are among all models we list, including older ones. The share is rounded up to whole models, so a rank slightly past the exact share still counts. Models with equal scores share the better rank.

Price by provider

The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.

ProviderInputOutputCached inputMixedNotes
Baidu $0.044$0.132 $0.0014 $0.066 27% cheaper fp8 · promo −90%
Relace $0.07$0.14 $0.014 $0.0875 3% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
DeepInfra Price used here $0.06$0.18 $0.015 $0.09 fp8
Wafer $0.0443$0.30 $0.035 $0.1082 US · nvfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
StreamLake $0.088$0.264 $0.0028 $0.132 fp8 · promo −80%
Cohere $0.11$0.22 $0.05 $0.1375 fp8
DigitalOcean $0.119$0.238 $0.0238 $0.1488
BaseTen $0.13$0.26 $0.028 $0.1625 fp8
Show all providers: 27
  • BaseTen: $0.13 / $0.26 · $0.1625
  • Venice: $0.13 / $0.26 · $0.1625
  • CoreWeave: $0.13 / $0.27 · $0.165
  • Nebius: $0.14 / $0.28 · $0.175
  • Parasail: $0.14 / $0.28 · $0.175
  • Reka: $0.10 / $0.42 · $0.18
  • Sail Research: $0.15 / $0.30 · $0.1875
  • Sail Research: $0.15 / $0.30 · $0.1875
  • Inceptron: $0.13 / $0.495 · $0.2213
  • Mancer 2: $0.15 / $0.50 · $0.2375
  • SiliconFlow: $0.22 / $0.66 · $0.33
  • GMICloud: $0.286 / $0.858 · $0.429
  • Alibaba: $0.352 / $1.06 · $0.528
  • Alibaba: $0.374 / $1.12 · $0.561
  • Novita: $0.418 / $1.25 · $0.627
  • AtlasCloud: $0.44 / $1.32 · $0.66
  • Chutes: $0.44 / $1.32 · $0.66
  • Cloudflare: $0.44 / $1.32 · $0.66
  • PrimeIntellect: $0.44 / $1.32 · $0.66

Other pricing modes

Specifications

Context window
1M
Max output
944k
Accepts
text
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Optional
Thinking effort levels: none, low, high, and max
Thinking is on by default
Weights on Hugging Face
Hugging Face A Hugging Face repository is linked. We did not check the licence; read it before you build on it.
Knowledge cutoff
No data
On OpenRouter since
July 31, 2026
Price check
disputed

As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.

Benchmark scores

Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.

SourceScoreRank among scored
Coding Index
Artificial Analysis, read November 18, 2026
69.1Rank 15 of 86, among scored models Top 25%
Agentic Index
Artificial Analysis, read November 18, 2026
41.0Rank 9 of 64, among scored models Top 25%
Websites
Design Arena, read November 21, 2026
1,225Rank 57 of 127, among scored models
UI components
Design Arena, read November 21, 2026
1,221Rank 53 of 118, among scored models
Game development
Design Arena, read November 21, 2026
1,187Rank 57 of 121, among scored models
3D scenes
Design Arena, read November 21, 2026
1,175Rank 54 of 114, among scored models
Data visualization
Design Arena, read November 21, 2026
1,166Rank 68 of 112, among scored models
SVG graphics
Design Arena, read November 21, 2026
1,164Rank 44 of 84, among scored models
ASCII art
Design Arena, read November 21, 2026
1,083Rank 62 of 68, among scored models
Code
Design Arena, read November 21, 2026
1,212Rank 58 of 122, among scored models

Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.

Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab

Sources and dates

Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.