DeepSeek V4 Pro 0423

DeepSeek · On OpenRouter since April 24, 2026 · Pinned version id: deepseek/deepseek-v4-pro-20260423

Price

$1.10

mixed / 1M tokens

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

in $0.90 · out $1.70 · Cached input $0.08

via SiliconFlow

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

Measured by a third party

Code: 1,224 · Rank 53 of 122, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.51

Hard questions and reasoning

Measured by a third party

Intelligence Index: 20.8 · Rank 43 of 66, among scored models · Artificial Analysis, read November 21, 2026

Cost of this job: $0.16

Models that score at least as high for less in this scenario: 13

Websites and apps

Measured by a third party

Websites: 1,223 · Rank 58 of 127, among scored models · Design Arena, read November 21, 2026

UI components: 1,205 · Rank 58 of 118, among scored models · Design Arena, read November 21, 2026

Web apps (agent): 1,000 · Rank 46 of 47, among scored models · Design Arena, read November 21, 2026

Full-stack apps (agent): 948 · Rank 45 of 45, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.20

Models that score at least as high for less in this scenario: 14

Games and 3D

Measured by a third party

Game development: 1,211 · Rank 48 of 121, among scored models · Design Arena, read November 21, 2026

3D scenes: 1,220 · Rank 40 of 114, among scored models · Design Arena, read November 21, 2026

Godot games (agent): 1,059 · Rank 30 of 34, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.20

Models that score at least as high for less in this scenario: 9

Charts and graphics

Measured by a third party

Data visualization: 1,197 · Rank 59 of 112, among scored models · Design Arena, read November 21, 2026

SVG graphics: 1,123 · Rank 57 of 84, among scored models · Design Arena, read November 21, 2026

ASCII art: 1,134 · Rank 46 of 68, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.20

Models that score at least as high for less in this scenario: 11

Long documents

Declared, not measured

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

Cost of this job: $1.10

The size of each job is our assumption; the prices are real.

  • Writing code: Requests: 40. Input tokens per request: 30,000. Output tokens per request: 1,500. Share of input served from cache: 70%.
  • Hard questions and reasoning: Requests: 10. Input tokens per request: 3,000. Output tokens per request: 8,000. Share of input served from cache: 0%.
  • Websites and apps; Games and 3D; Charts and graphics: Requests: 8. Input tokens per request: 12,000. Output tokens per request: 10,000. Share of input served from cache: 30%.
  • Long documents: Requests: 3. Input tokens per request: 400,000. Output tokens per request: 4,000. Share of input served from cache: 0%.

Thinking is billed as output tokens; a model that thinks longer costs more than this estimate. Ranks are among all models we list, including older ones.

Cheaper models with a similar benchmark score

Rule: an Intelligence Index of at least 17.8, a mixed price at least 25% lower, at least the same input types, and tool support. Lower mixed price (3 input tokens to 1 output token); check the flags and your own prompt sizes.

  1. Ling 3.1 Flash inclusionAI 92% cheaper $0.09 · Index 29.6 (this model: 20.8) Differences to check: No structured output Compare
  2. Inkling 2 Mini Thinking Machines 86% cheaper $0.1588 · Index 20.1 (this model: 20.8) Differences to check: Lower max output Compare
  3. MiMo-V2.6-Flash Xiaomi 84% cheaper $0.175 · Index 26.7 (this model: 20.8) Differences to check: Lower max output Compare
  4. Claude Haiku 5.5 Anthropic 82% cheaper $0.20 · Index 36.5 (this model: 20.8) Differences to check: Lower max output; Price rises for long prompts Compare
  5. Muse Ember Meta 82% cheaper $0.20 · Index 36.0 (this model: 20.8) Compare
Show more: 10
  1. GPT-6 Luna OpenAI 82% cheaper $0.20 · Index 27.9 (this model: 20.8) Differences to check: Lower max output; Price rises for long prompts Compare
  2. Qwen3.8 Flash Qwen 79% cheaper $0.23 · Index 28.6 (this model: 20.8) Differences to check: Lower max output Compare
  3. GLM 5.3 Flash Z.ai 78% cheaper $0.2375 · Index 27.8 (this model: 20.8) Differences to check: Lower max output Compare
  4. MiniMax M3.1 Flash MiniMax 76% cheaper $0.2625 · Index 29.1 (this model: 20.8) Compare
  5. GPT-5.6 Luna OpenAI 59% cheaper $0.45 · Index 23.8 (this model: 20.8) Differences to check: Lower max output; Price rises for long prompts Compare
  6. Inkling 2 Small Thinking Machines 57% cheaper $0.475 · Index 30.6 (this model: 20.8) Compare
  7. DeepSeek V4.1 Flash 1017 DeepSeek 52% cheaper $0.525 · Index 32.6 (this model: 20.8) Compare
  8. MiniMax M3 MiniMax 52% cheaper $0.525 · Index 18.9 (this model: 20.8) Compare
  9. MiMo-V2.6-Pro Xiaomi 51% cheaper $0.5438 · Index 29.9 (this model: 20.8) Differences to check: Lower max output Compare
  10. Hy4 Tencent 43% cheaper $0.6254 · Index 34.6 (this model: 20.8) Differences to check: Lower max output Compare

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 $0.6608$1.32 $0.0547 $0.826 25% cheaper fp8 · promo −61%
StreamLake $0.6622$1.32 $0.0552 $0.8278 25% cheaper fp8 · promo −62%
Relace $0.90$1.50 $0.20 $1.05 5% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
SiliconFlow Price used here $0.90$1.70 $0.08 $1.10 fp8
GMICloud $0.957$1.91 $0.0798 $1.20 fp8 · promo −45%
DigitalOcean $1.04$2.09 $0.2088 $1.31
Novita $1.28$2.56 $0.108 $1.60 fp8 · promo −20%
DeepInfra $1.30$2.60 $0.10 $1.63 fp8
Show all providers: 13
  • Alibaba: $1.42 / $2.83 · $1.77
  • Alibaba: $1.56 / $3.12 · $1.95
  • Venice: $1.65 / $3.30 · $2.06
  • AtlasCloud: $1.68 / $3.38 · $2.11
  • Azure: $1.91 / $3.83 · $2.39

Other pricing modes

Specifications

Context window
1M
Max output
393k
Accepts
text
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Optional
Thinking effort levels: none, high, and xhigh
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
April 24, 2026
Price check
one source

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
Intelligence Index
Artificial Analysis, read November 21, 2026
20.8Rank 43 of 66, among scored models
Websites
Design Arena, read November 21, 2026
1,223Rank 58 of 127, among scored models
UI components
Design Arena, read November 21, 2026
1,205Rank 58 of 118, among scored models
Game development
Design Arena, read November 21, 2026
1,211Rank 48 of 121, among scored models
3D scenes
Design Arena, read November 21, 2026
1,220Rank 40 of 114, among scored models
Data visualization
Design Arena, read November 21, 2026
1,197Rank 59 of 112, among scored models
SVG graphics
Design Arena, read November 21, 2026
1,123Rank 57 of 84, among scored models
ASCII art
Design Arena, read November 21, 2026
1,134Rank 46 of 68, among scored models
Code
Design Arena, read November 21, 2026
1,224Rank 53 of 122, among scored models
Web apps (agent)
Design Arena, read November 21, 2026
1,000Rank 46 of 47, among scored models
Full-stack apps (agent)
Design Arena, read November 21, 2026
948Rank 45 of 45, among scored models
Godot games (agent)
Design Arena, read November 21, 2026
1,059Rank 30 of 34, 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.