Get started

Gemini 3.5 Flash (batch) against Claude Fable 5.2.

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 3.5 Flash (batch)vsClaude Fable 5.2USD per 1M tokens · one scale
Listed
1,048,576 tokens
Context
1,000,000 tokens
65,536 tokens
Max output
128,000 tokens
text, image, video, file, audio → text
Modalities
text, image, file → text
2025-01-01
Knowledge cutoff
not stated
137 tok/s
Throughput
84.9 tok/s
1.39s
First token
4.71s
15,096 requests · 7 endpoints
Timed over
12,305 requests · 5 endpoints

Listed price

USD per million tokens · one linear scale
Gemini 3.5 Flash (batch)Google · listed 19 May 2026
Input per M$0.75
Cached input per M$0.075
Output per M$4.50
Blended, 3 in to 1 out$1.688
Claude Fable 5.2Anthropic · listed 9 Nov 2026
Input per M$8.00
Cached input per M$0.20
Output per M$40.00
Blended, 3 in to 1 out$16.00

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

28 boards
not scored
Intelligence Index
64.6 · 01 of 58
70.1 · 25 of 118
Coding Index
not scored
26.0 · 33 of 94
Agentic Index
not scored
1259 · 35 of 126
Websites · Models
1350 · 03 of 126
1255 · 38 of 120
Code · Models
1374 · 03 of 120
1253 · 35 of 120
Game development · Models
1401 · 05 of 120
1264 · 35 of 116
UI components · Models
1378 · 03 of 116
1225 · 40 of 113
3D scenes · Models
1498 · 01 of 113
1238 · 38 of 110
Data visualisation · Models
not ranked
1245 · 19 of 83
SVG · Models
not ranked
1237 · 19 of 67
ASCII art · Models
not ranked
1169 · 28 of 49
Mobile apps · Agents
1318 · 02 of 49
1181 · 26 of 47
Web apps · Agents
not ranked
1170 · 21 of 44
Full stack · Agents
1397 · 01 of 44
1174 · 19 of 41
Android native · Agents
not ranked
1148 · 27 of 36
pdf · Agents
1351 · 01 of 36
1069 · 29 of 34
Godot game development · Agents
not ranked
985 · 30 of 32
spreadsheet · Agents
1429 · 01 of 32
1247 · 06 of 29
python-pptx slides · Agents
not ranked
1168 · 16 of 26
codetovideo · Agents
1445 · 01 of 26
1126 · 13 of 25
Agentic game development · Agents
not ranked
904 · 24 of 25
blender3d · Agents
not ranked
1040 · 21 of 25
HTML slides · Agents
not ranked
1162 · 06 of 9
Agentic HTML slides · Agents
not ranked
1244 · 03 of 9
Agentic slides · Agents
not ranked
1162 · 06 of 9
Agentic slides, HTML · Agents
not ranked
1242 · 02 of 9
Agentic slides, python-pptx · Agents
not ranked
1244 · 02 of 8
PPTX slides · 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
Gemini 3.5 Flash (batch)$0.001500$1.50$150
Claude Fable 5.2$0.0144$14.40$1,440

Gemini 3.5 Flash (batch) costs 90% 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.