Get started

Kimi K3.1 Pro against Muse Spark 1.3.

Two listings from the same committed catalog, side by side: the fields OpenRouter publishes, the boards two third parties scored, and a cost sheet that is arithmetic over the listed rates.

retrieved sha256 · 0bb53a77713f

Compare/Kimi K3.1 ProvsMuse Spark 1.3USD per 1M tokens · one scale
Listed
1,048,576 tokens
Context
1,048,576 tokens
943,718 tokens
Max output
943,718 tokens
text, image, video → text
Modalities
text, image, video, file → text
not stated
Knowledge cutoff
not stated
82.7 tok/s
Throughput
106 tok/s
1.07s
First token
2.71s
141,675 requests · 28 endpoints
Timed over
8,506 requests · 2 endpoints

Listed price

USD per million tokens · one linear scale
Kimi K3.1 ProMoonshotAI · listed 23 Oct 2026
Input per M$0.24
Cached input per M$0.20
Output per M$8.40
Blended, 3 in to 1 out$2.281
Muse Spark 1.3Meta · listed 2 Sep 2026
Input per M$1.25
Cached input per M$0.15
Output per M$4.25
Blended, 3 in to 1 out$2.00

Per million tokens, as OpenRouter listed them when the catalog was read: its routed rates, not a provider's own page. One linear scale across every row, so a bar twice as long is twice the price. The blended row is Vitna's arithmetic, three input tokens to one output.

Every board either stands on

21 boards
46.5 · 11 of 58
Intelligence Index
36.6 · 15 of 58
not scored
Coding Index
75.8 · 11 of 118
not scored
Agentic Index
55.5 · 04 of 94
1319 · 07 of 126
Websites · Models
1359 · 02 of 126
1348 · 07 of 120
Code · Models
1352 · 05 of 120
1402 · 04 of 120
Game development · Models
1344 · 11 of 120
1390 · 01 of 116
UI components · Models
1350 · 07 of 116
1440 · 03 of 113
3D scenes · Models
1381 · 10 of 113
1293 · 13 of 110
Data visualisation · Models
1342 · 06 of 110
1324 · 04 of 83
SVG · Models
1314 · 06 of 83
1296 · 08 of 67
ASCII art · Models
1320 · 05 of 67
1267 · 05 of 49
Mobile apps · Agents
1208 · 16 of 49
1307 · 03 of 47
Web apps · Agents
1288 · 05 of 47
1321 · 03 of 44
Full stack · Agents
1287 · 06 of 44
1157 · 24 of 41
Android native · Agents
1300 · 02 of 41
1222 · 13 of 36
pdf · Agents
1203 · 17 of 36
not ranked
Godot game development · Agents
1210 · 09 of 34
1318 · 04 of 32
spreadsheet · Agents
1124 · 17 of 32
1286 · 03 of 29
python-pptx slides · Agents
1212 · 11 of 29
1255 · 08 of 26
codetovideo · Agents
1217 · 11 of 26
not ranked
blender3d · Agents
1145 · 08 of 25

Score and position on each board, from the board's own source as OpenRouter carries it. The heavier figure leads that board; a missing score is a fact about coverage, not a zero.

Cost sheet

800 in · 200 out per call

Arithmetic over the listed rates and nothing else: tokens in over one million times the input rate, plus tokens out over one million times the output rate. No cache, no retries and no failure rate assumed; the Decision Lab is where cost per successful unit lives.

ModelPer callPer 1,000 callsPer 100,000 calls
Kimi K3.1 Pro$0.001873$1.87$187
Muse Spark 1.3$0.001850$1.85$185

Muse Spark 1.3 costs 1% less per call at these token counts.

Other pairs with a page
For one of your workloads

The market on these two is here. The right one for your work is not.

What this page cannot say is which is right for a particular piece of your production work, because that depends on what the workload requires and what your own evaluations measured, neither of which is public. The register weighs a candidate against a workload's own thresholds and shows what the engine would decide before anything is filed.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.