Get started

Gemini 4 Argon 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/Gemini 4 ArgonvsQwen3.8 Max (0902)USD per 1M tokens · one scale
Listed
1,048,576 tokens
Context
1,000,000 tokens
943,718 tokens
Max output
131,072 tokens
audio, file, image, text, video → text
Modalities
text, image, video → text
not stated
Knowledge cutoff
not stated
38.4 tok/s
Throughput
37.6 tok/s
4.68s
First token
2.75s
47,737 requests · 6 endpoints
Timed over
3,678 requests · 2 endpoints

Listed price

USD per million tokens · one linear scale
Gemini 4 ArgonGoogle · listed 13 Oct 2026
Input per M$2.00
Cached input per M$0.10
Output per M$10.00
Blended, 3 in to 1 out$4.00
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

16 boards
50.4 · 09 of 58
Intelligence Index
33.7 · 19 of 58
not scored
Coding Index
76.2 · 08 of 118
not scored
Agentic Index
56.0 · 03 of 94
1316 · 08 of 126
Websites · Models
not ranked
1326 · 12 of 120
Code · Models
not ranked
1361 · 08 of 120
Game development · Models
not ranked
1330 · 14 of 116
UI components · Models
not ranked
1354 · 12 of 113
3D scenes · Models
not ranked
1323 · 10 of 110
Data visualisation · Models
not ranked
1339 · 02 of 83
SVG · Models
not ranked
1283 · 07 of 47
Web apps · Agents
not ranked
1282 · 04 of 36
pdf · Agents
not ranked
1146 · 16 of 32
spreadsheet · Agents
not ranked
1266 · 06 of 26
codetovideo · Agents
not ranked
1266 · 01 of 25
Agentic game development · Agents
not ranked
1347 · 01 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.

Vitna reads

from provider pages

Where the registry tracks a model, Vitna reads the rate from the provider page itself and keeps it as a dated record; the OpenRouter figures above are its routed rates.

Google · Gemini 4 Argon$2.00 / $10.00

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
Gemini 4 Argon$0.003600$3.60$360
Qwen3.8 Max (0902)$0.002800$2.80$280

Qwen3.8 Max (0902) costs 22% 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.