Claude Opus 5.5 (batch)
Sold by 6 sellers, timed at 80.8 tok/s, scored 59.1 on the Intelligence Index, and on 16 Design Arena boards.
retrieved sha256 · 0bb53a77713f
What sellers charge
6 sellers · 2x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $4.00 at Amazon Bedrock to $8.00 at Anthropic. The $2.00 listed is the cheapest on offer; 6 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
134,352 requests · 11 endpoints · 30-minute windowOpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.
Every endpoint
11 priced · 11 timed · cheapest first- Amazon Bedrockamazon-bedrock$4.00$20.00$0.20not declared128k65 tok/s314.39s36 req100%
- Amazon Bedrockamazon-bedrock$4.00$20.00$0.20not declared128k71 tok/s361.43s35,741 req100%
- Amazon Bedrockamazon-bedrock$4.00$20.00$0.20not declared128k79 tok/s462.91s1,108 req100%
- Anthropicanthropic$4.00$20.00$0.20not declared128knot matchednonenonenot matched100%
- Azureazure/global$4.00$20.00$0.20not declared128k81 tok/s81766ms2 req100%
- Azureazure/global$4.00$20.00$0.20not declared128k86.5 tok/s55.92.4s195 req100%
- Claude Platform on AWSclaude-on-aws$4.00$20.00$0.20not declared128k83 tok/s492.84s35,012 req100%
- Googlegoogle-vertex/global$4.00$20.00$0.20not declared128k98 tok/s74.12.67s204 req100%
- Googlegoogle-vertex/global$4.00$20.00$0.20not declared128k91 tok/s521.12s4 req100%
- Googlegoogle-vertex/global$4.00$20.00$0.20not declared128k83 tok/s441.38s17,131 req100%
- Anthropicanthropic/fast$8.00$40.00$0.40not declared128knot matchednonenonenot matched100%
- Anthropicnot matchednot matchednot matchednot matchedno offer84 tok/s472.32s44,235 reqno offer
- Anthropicnot matchednot matchednot matchednot matchedno offer214 tok/s77.81.52s684 reqno offer
Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 3 of the 11 timed routes are slower than it, and the middle route runs at 83 tok/s. The widest median-to-p90 gap is Anthropic's, 2.75x.
Anthropic publishes 2 offers and had 2 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.
Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 4 of the 11 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Anthropic (anthropic/fast) at 96.97% on 13 Nov 2026, Anthropic (anthropic) at 97.22% on 13 Nov 2026, Azure (azure/global) at 97.48% on 13 Nov 2026, and Amazon Bedrock (amazon-bedrock/us-east-1) at 98.77% on 14 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.
Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .
What each seller accepts
11 parameters · 6 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- stopevery seller
- tool_choiceevery seller
- toolsevery seller
- verbosityevery seller
- structured_outputs5 of 6not Amazon Bedrock
- max_completion_tokens1 of 6only Azure
9 of these 11 are accepted by every one of the 6 sellers that publish a list; the other 2 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $4.00 per million tokens, 3 in to 1 out: cheaper than 55 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.
Measured quality
145 models with an index · 132 on a design arena boardEach mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.
- Android native · Agents1389 Elowin rate 74.2% · source rank 1the board, 41 ranked
- blender3d · Agents1225 Elowin rate 57.6% · source rank 4the board, 25 ranked
- codetovideo · Agents1351 Elowin rate 73.0% · source rank 2the board, 26 ranked
- Full stack · Agents1391 Elowin rate 70.9% · source rank 2the board, 44 ranked
- Mobile apps · Agents1294 Elowin rate 61.9% · source rank 3the board, 49 ranked
- pdf · Agents1316 Elowin rate 68.0% · source rank 2the board, 36 ranked
- spreadsheet · Agents1291 Elowin rate 53.1% · source rank 6the board, 32 ranked
- Web apps · Agents1319 Elowin rate 62.6% · source rank 2the board, 47 ranked
- 3D scenes · Models1462 Elowin rate 65.1% · source rank 2the board, 113 ranked
- ASCII art · Models1349 Elowin rate 64.8% · source rank 3the board, 67 ranked
- Code · Models1384 Elowin rate 60.9% · source rank 2the board, 120 ranked
- Data visualisation · Models1385 Elowin rate 63.8% · source rank 1the board, 110 ranked
- Game development · Models1427 Elowin rate 63.9% · source rank 1the board, 120 ranked
- SVG · Models1321 Elowin rate 54.0% · source rank 5the board, 83 ranked
- UI components · Models1375 Elowin rate 63.1% · source rank 4the board, 116 ranked
- Websites · Models1325 Elowin rate 55.6% · source rank 6the board, 126 ranked
Position 5 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.
Benchmark results
none of 6 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for Claude Opus 5.5 (batch) under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.
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.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.
