Get started

Claude Sonnet 5.5 against Gemini 4 Carbon.

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/Claude Sonnet 5.5vsGemini 4 CarbonUSD per 1M tokens · one scale
Listed
1,000,000 tokens
Context
1,048,576 tokens
128,000 tokens
Max output
943,718 tokens
text, image, file → text
Modalities
audio, file, image, text, video → text
not stated
Knowledge cutoff
not stated
103 tok/s
Throughput
41.7 tok/s
1.51s
First token
8.86s
121,497 requests · 10 endpoints
Timed over
106,752 requests · 7 endpoints

Listed price

USD per million tokens · one linear scale
Claude Sonnet 5.5Anthropic · listed 28 Sep 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
Gemini 4 CarbonGoogle · listed 10 Nov 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

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

15 boards
54.5 · 06 of 58
Intelligence Index
60.0 · 02 of 58
1306 · 13 of 126
Websites · Models
1311 · 10 of 126
1343 · 08 of 120
Code · Models
1341 · 09 of 120
1383 · 06 of 120
Game development · Models
1332 · 12 of 120
1387 · 02 of 116
UI components · Models
1345 · 08 of 116
1403 · 08 of 113
3D scenes · Models
1424 · 06 of 113
1362 · 03 of 110
Data visualisation · Models
not ranked
1300 · 08 of 83
SVG · Models
1400 · 01 of 83
1259 · 06 of 49
Mobile apps · Agents
1292 · 04 of 49
1297 · 04 of 47
Web apps · Agents
not ranked
1260 · 06 of 41
Android native · Agents
not ranked
1247 · 10 of 36
pdf · Agents
1305 · 03 of 36
1253 · 10 of 32
spreadsheet · Agents
1220 · 13 of 32
1327 · 03 of 26
codetovideo · Agents
1287 · 05 of 26
1237 · 03 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.

Anthropic · Claude Sonnet 5.5$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
Claude Sonnet 5.5$0.003600$3.60$360
Gemini 4 Carbon$0.003600$3.60$360

The two cost the same 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.