DeepSeek V4.1 Flash 1017

DeepSeek · On OpenRouter since October 17, 2026 · Pinned version id: deepseek/deepseek-v4.1-flash-20261017

Price

$0.525

mixed / 1M tokens

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

in $0.30 · out $1.20 · Cached input $0.006

Cheaper off-peak. This provider changes the price during the day or week. The higher rate is shown.

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

Code: 1,281 · Rank 22 of 122, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.19

Hard questions and reasoning

Measured by a third party

Intelligence Index: 32.6 · Rank 25 of 66, among scored models · Artificial Analysis, read November 21, 2026

Cost of this job: $0.11

Models that score at least as high for less in this scenario: 2

Websites and apps Top 25%

Measured by a third party

Websites: 1,289 · Rank 21 of 127, among scored models · Top 25% · Design Arena, read November 21, 2026

UI components: 1,274 · Rank 28 of 118, among scored models · Top 25% · Design Arena, read November 21, 2026

Cost of this job: $0.12

Models that score at least as high for less in this scenario: 2

Games and 3D

Measured by a third party

Game development: 1,248 · Rank 32 of 121, among scored models · Design Arena, read November 21, 2026

3D scenes: 1,332 · Rank 16 of 114, among scored models · Top 25% · Design Arena, read November 21, 2026

Cost of this job: $0.12

Models that score at least as high for less in this scenario: 4

Slides and spreadsheets

Measured by a third party

Spreadsheets (agent): 1,263 · Rank 9 of 32, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.12

Charts and graphics Top 25%

Measured by a third party

Data visualization: 1,271 · Rank 26 of 112, among scored models · Top 25% · Design Arena, read November 21, 2026

SVG graphics: 1,235 · Rank 22 of 84, among scored models · Design Arena, read November 21, 2026

ASCII art: 1,222 · Rank 23 of 68, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.12

Models that score at least as high for less in this scenario: 3

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: $0.37

Images, files, audio, video in

Declared, not measured

Accepts: images. Declared by the provider through OpenRouter; we did not test it.

Cost of this job: $0.12Text-token prices only; images, audio and video may be billed separately.

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; Slides and spreadsheets; 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%.
  • Images, files, audio, video in: Requests: 15. Input tokens per request: 20,000. Output tokens per request: 3,000. Share of input served from cache: 30%.

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. 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.

Cheaper models with a similar benchmark score

Rule: an Intelligence Index of at least 29.6, 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. Claude Haiku 5.5 Anthropic 62% cheaper $0.20 · Index 36.5 (this model: 32.6) Differences to check: Lower max output; Price rises for long prompts Compare
  2. Muse Ember Meta 62% cheaper $0.20 · Index 36.0 (this model: 32.6) 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
Sail Research $0.04$0.10 $0.007 $0.055 90% cheaper US · fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Sail Research $0.04$0.10 $0.007 $0.055 90% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Ambient $0.045$0.25 $0.0025 $0.0963 82% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Pearl Research $0.05$0.30 $0.003 $0.1125 79% cheaper fp8
DeepInfra $0.098$0.294 $0.0029 $0.147 72% cheaper fp8 · promo −51%
Wafer $0.036$0.50 $0.01 $0.152 71% cheaper US · mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Morph $0.059$0.52 $0.005 $0.1743 67% cheaper fp8
Wafer $0.066$0.50 $0.0065 $0.1745 67% cheaper mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Show all providers: 48
  • Tenstorrent: $0.10 / $0.40 · $0.175
  • Particle AI: $0.06 / $0.55 · $0.1825
  • StepFun: $0.105 / $0.42 · $0.1838
  • Cohere: $0.115 / $0.40 · $0.1863
  • StreamLake: $0.111 / $0.444 · $0.1943
  • PrimeIntellect: $0.0437 / $0.70 · $0.2078
  • Ant Digital: $0.12 / $0.48 · $0.21
  • River: $0.12 / $0.48 · $0.21
  • Relace: $0.12 / $0.50 · $0.215
  • Cloudflare: $0.10 / $0.60 · $0.225
  • DekaLLM: $0.10 / $0.60 · $0.225
  • Inceptron: $0.10 / $0.60 · $0.225
  • Inference.net: $0.08 / $0.666 · $0.2265
  • Inference.net: $0.08 / $0.666 · $0.2265
  • OpenInference: $0.06 / $0.80 · $0.245
  • DigitalOcean: $0.15 / $0.60 · $0.2625
  • SiliconFlow: $0.15 / $0.60 · $0.2625
  • Baidu: $0.1498 / $0.6046 · $0.2635
  • Novita: $0.165 / $0.66 · $0.2888
  • ModelRun: $0.17 / $0.67 · $0.295
  • Ionstream: $0.21 / $0.62 · $0.3125
  • Makora: $0.15 / $0.80 · $0.3125
  • Alibaba: $0.18 / $0.72 · $0.315
  • GMICloud: $0.18 / $0.72 · $0.315
  • Nebius: $0.18 / $0.72 · $0.315
  • AtlasCloud: $0.195 / $0.78 · $0.3413
  • PrimaLabs: $0.24 / $0.96 · $0.42
  • Modal: $0.25 / $1.00 · $0.4375
  • Crusoe: $0.29 / $1.20 · $0.5175
  • DeepSeek: $0.30 / $1.20 · $0.525
  • BaseTen: $0.30 / $1.20 · $0.525
  • CoreWeave: $0.30 / $1.20 · $0.525
  • Fireworks: $0.30 / $1.20 · $0.525
  • Mistral: $0.30 / $1.20 · $0.525
  • Near AI: $0.30 / $1.20 · $0.525
  • Parasail: $0.30 / $1.20 · $0.525
  • Reka: $0.30 / $1.20 · $0.525
  • Together: $0.30 / $1.20 · $0.525
  • Venice: $0.30 / $1.20 · $0.525
  • Fireworks: $0.45 / $1.80 · $0.7875

Other pricing modes

Specifications

Context window
1M
Max output
393k
Accepts
text and images
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
October 17, 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
32.6Rank 25 of 66, among scored models
Websites
Design Arena, read November 21, 2026
1,289Rank 21 of 127, among scored models Top 25%
UI components
Design Arena, read November 21, 2026
1,274Rank 28 of 118, among scored models Top 25%
Game development
Design Arena, read November 21, 2026
1,248Rank 32 of 121, among scored models
3D scenes
Design Arena, read November 21, 2026
1,332Rank 16 of 114, among scored models Top 25%
Data visualization
Design Arena, read November 21, 2026
1,271Rank 26 of 112, among scored models Top 25%
SVG graphics
Design Arena, read November 21, 2026
1,235Rank 22 of 84, among scored models
ASCII art
Design Arena, read November 21, 2026
1,222Rank 23 of 68, among scored models
Code
Design Arena, read November 21, 2026
1,281Rank 22 of 122, among scored models Top 25%
Spreadsheets (agent)
Design Arena, read November 21, 2026
1,263Rank 9 of 32, 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.