Kimi K3.1 Pro

MoonshotAI · On OpenRouter since October 23, 2026 · Pinned version id: moonshotai/kimi-k3.1-pro-20261023

Price

$4.00

mixed / 1M tokens

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

in $2.00 · out $10.00 · Cached input $0.20

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 10%

Measured by a third party

Code: 1,342 · Rank 8 of 122, among scored models · Design Arena, read November 21, 2026

Cost of this job: $1.53

Hard questions and reasoning Top 25%

Measured by a third party

Intelligence Index: 46.5 · Rank 14 of 66, among scored models · Artificial Analysis, read November 21, 2026

Cost of this job: $0.86

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

Websites and apps Top 10%

Measured by a third party

Websites: 1,314 · Rank 9 of 127, among scored models · Top 10% · Design Arena, read November 21, 2026

UI components: 1,374 · Rank 3 of 118, among scored models · Top 10% · Design Arena, read November 21, 2026

Web apps (agent): 1,297 · Rank 3 of 47, among scored models · Top 10% · Design Arena, read November 21, 2026

Full-stack apps (agent): 1,320 · Rank 4 of 45, among scored models · Top 10% · Design Arena, read November 21, 2026

Mobile apps (agent): 1,267 · Rank 5 of 50, among scored models · Top 10% · Design Arena, read November 21, 2026

Android apps (agent): 1,164 · Rank 23 of 41, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.95

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

Games and 3D Top 10%

Measured by a third party

Game development: 1,390 · Rank 5 of 121, among scored models · Top 10% · Design Arena, read November 21, 2026

3D scenes: 1,431 · Rank 4 of 114, among scored models · Top 10% · Design Arena, read November 21, 2026

Cost of this job: $0.95

Models that score at least as high for less in this scenario: 1

Slides and spreadsheets

Measured by a third party

PowerPoint files (agent): 1,287 · Rank 3 of 29, among scored models · Design Arena, read November 21, 2026

Spreadsheets (agent): 1,315 · Rank 4 of 32, among scored models · Top 10% · Design Arena, read November 21, 2026

Cost of this job: $0.95

Charts and graphics Top 25%

Measured by a third party

Data visualization: 1,295 · Rank 15 of 112, among scored models · Top 25% · Design Arena, read November 21, 2026

SVG graphics: 1,321 · Rank 4 of 84, among scored models · Top 10% · Design Arena, read November 21, 2026

ASCII art: 1,302 · Rank 9 of 68, among scored models · Top 25% · Design Arena, read November 21, 2026

Cost of this job: $0.95

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

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: $2.52

Images, files, audio, video in

Declared, not measured

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

Cost of this job: $0.90Text-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 43.5, 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. Gemini 4 Hydrogen Google 25% cheaper $3.00 · Index 53.9 (this model: 46.5) 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
Relace $0.2403$8.40 $0.20 $2.28 43% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Wafer $0.253$8.80 $0.18 $2.39 40% cheaper US · mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Decart $1.20$6.00 $0.12 $2.40 40% cheaper mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. · promo −40%
Sail Research $1.04$9.35 $0.187 $3.12 22% cheaper US · fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Morph $1.38$9.00 $0.172 $3.28 18% cheaper fp8
Sail Research $1.40$9.35 $0.187 $3.39 15% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Inference.net $1.80$9.00 $0.198 $3.60 10% cheaper mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Inference.net $1.80$9.00 $0.198 $3.60 10% cheaper US · mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Show all providers: 24
  • Wafer: $1.80 / $9.00 · $3.60
  • DeepInfra: $1.90 / $9.50 · $3.80
  • DigitalOcean: $1.90 / $9.50 · $3.80
  • AkashML: $1.75 / $10.00 · $3.81
  • Makora: $2.00 / $9.49 · $3.87
  • MoonshotAI: $2.00 / $10.00 · $4.00
  • Alibaba: $2.00 / $10.00 · $4.00
  • Fireworks: $2.00 / $10.00 · $4.00
  • Modal: $2.00 / $10.00 · $4.00
  • Nebius: $2.00 / $10.00 · $4.00
  • Parasail: $2.00 / $10.00 · $4.00
  • PrimaLabs: $2.00 / $10.00 · $4.00
  • River: $2.00 / $10.00 · $4.00
  • Together: $2.00 / $10.00 · $4.00
  • Amazon Bedrock: $4.00 / $20.00 · $8.00
  • Amazon Bedrock: $4.40 / $22.00 · $8.80

Other pricing modes

Specifications

Context window
1M
Max output
944k
Accepts
text, images, and video
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 23, 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
46.5Rank 14 of 66, among scored models Top 25%
Websites
Design Arena, read November 21, 2026
1,314Rank 9 of 127, among scored models Top 10%
UI components
Design Arena, read November 21, 2026
1,374Rank 3 of 118, among scored models Top 10%
Game development
Design Arena, read November 21, 2026
1,390Rank 5 of 121, among scored models Top 10%
3D scenes
Design Arena, read November 21, 2026
1,431Rank 4 of 114, among scored models Top 10%
Data visualization
Design Arena, read November 21, 2026
1,295Rank 15 of 112, among scored models Top 25%
SVG graphics
Design Arena, read November 21, 2026
1,321Rank 4 of 84, among scored models Top 10%
ASCII art
Design Arena, read November 21, 2026
1,302Rank 9 of 68, among scored models Top 25%
Code
Design Arena, read November 21, 2026
1,342Rank 8 of 122, among scored models Top 10%
Web apps (agent)
Design Arena, read November 21, 2026
1,297Rank 3 of 47, among scored models Top 10%
Full-stack apps (agent)
Design Arena, read November 21, 2026
1,320Rank 4 of 45, among scored models Top 10%
Mobile apps (agent)
Design Arena, read November 21, 2026
1,267Rank 5 of 50, among scored models Top 10%
Android apps (agent)
Design Arena, read November 21, 2026
1,164Rank 23 of 41, among scored models
PowerPoint files (agent)
Design Arena, read November 21, 2026
1,287Rank 3 of 29, among scored models
Spreadsheets (agent)
Design Arena, read November 21, 2026
1,315Rank 4 of 32, among scored models Top 10%
agents/codetovideo
Design Arena, read November 21, 2026
1,241Rating 1,241; rank 9 at the source. Too few scored models for a tier.
agents/pdf
Design Arena, read November 21, 2026
1,229Rating 1,229; rank 13 at the source. Too few scored models for a tier.

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.