Get started

Muse Spark 1.3 against Qwen3.8 Max (0902).

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/Muse Spark 1.3vsQwen3.8 Max (0902)USD per 1M tokens · one scale
Author
Listed
1,048,576 tokens
Context
1,000,000 tokens
943,718 tokens
Max output
131,072 tokens
text, image, video, file → text
Modalities
text, image, video → text
not stated
Knowledge cutoff
not stated
106 tok/s
Throughput
37.6 tok/s
2.71s
First token
2.75s
8,506 requests · 2 endpoints
Timed over
3,678 requests · 2 endpoints

Listed price

USD per million tokens · one linear scale
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
Qwen3.8 Max (0902)Qwen · listed 3 Sep 2026
Input per M$2.00
Cached input per M$0.25
Output per M$6.00
Blended, 3 in to 1 out$3.00

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
36.6 · 15 of 58
Intelligence Index
33.7 · 19 of 58
75.8 · 11 of 118
Coding Index
76.2 · 08 of 118
55.5 · 04 of 94
Agentic Index
56.0 · 03 of 94
1359 · 02 of 126
Websites · Models
not ranked
1352 · 05 of 120
Code · Models
not ranked
1344 · 11 of 120
Game development · Models
not ranked
1350 · 07 of 116
UI components · Models
not ranked
1381 · 10 of 113
3D scenes · Models
not ranked
1342 · 06 of 110
Data visualisation · Models
not ranked
1314 · 06 of 83
SVG · Models
not ranked
1320 · 05 of 67
ASCII art · Models
not ranked
1208 · 16 of 49
Mobile apps · Agents
not ranked
1288 · 05 of 47
Web apps · Agents
not ranked
1287 · 06 of 44
Full stack · Agents
not ranked
1300 · 02 of 41
Android native · Agents
not ranked
1203 · 17 of 36
pdf · Agents
not ranked
1210 · 09 of 34
Godot game development · Agents
not ranked
1124 · 17 of 32
spreadsheet · Agents
not ranked
1212 · 11 of 29
python-pptx slides · Agents
not ranked
1217 · 11 of 26
codetovideo · Agents
not ranked
1145 · 08 of 25
blender3d · Agents
not ranked

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
Muse Spark 1.3$0.001850$1.85$185
Qwen3.8 Max (0902)$0.002800$2.80$280

Muse Spark 1.3 costs 34% 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.