Get started

Claude Sonnet 5.5 (batch)

Timed at 103 tok/s, scored 54.5 on the Intelligence Index, and on 14 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Sonnet 5.5 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-sonnet-5.5:batchAnthropic · batch variant · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$1.00per 1M tokens
Output$5.00per 1M tokens
Cached input$0.05per 1M tokens
Context1M1,000,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states3 meters
Cache write$1.25per 1M tokens
Cache write, 1 hour$2.00per 1M tokens
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-sonnet-5.5-20260928
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningalways on · effort max, xhigh, high, medium, low, high by default
Moderationmoderated by OpenRouter
Variantbatch
Other listingbase listing

Measured speed

121,497 requests · 10 endpoints · 30-minute window
Throughput103 tok/sMedian output rate, weighted across the 10 endpoints serving it by the requests each answered.the speed board
First token1.51sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread80.5 to 117The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter'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

10 priced · 10 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock$2.00$10.00$0.10not declared128k105 tok/s60.42.46s666 req100%
  2. Amazon Bedrockamazon-bedrock$2.00$10.00$0.10not declared128k80.5 tok/s39.51.48s108 req100%
  3. Amazon Bedrockamazon-bedrock$2.00$10.00$0.10not declared128k89 tok/s442.44s19,957 req100%
  4. Anthropicanthropic$2.00$10.00$0.10not declared128k100 tok/s501.54s24,365 req100%
  5. Azureazure/global$2.00$10.00$0.10not declared128k99 tok/s77.81.53s8 req100%
  6. Azureazure/global$2.00$10.00$0.10not declared128k117 tok/s62985ms7,658 req100%
  7. Claude Platform on AWSclaude-on-aws$2.00$10.00$0.10not declared128k106 tok/s631.14s52,864 req100%
  8. Googlegoogle-vertex/global$2.00$10.00$0.10not declared128k112 tok/s651.8s14,149 req100%
  9. Googlegoogle-vertex/global$2.00$10.00$0.10not declared128k96 tok/s62701ms1,581 req100%
  10. Googlegoogle-vertex/global$2.00$10.00$0.10not declared128k103 tok/s70.51.07s141 req100%

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: 6 of the 10 timed routes are slower than it, and the middle route runs at 101 tok/s. The widest median-to-p90 gap is Amazon Bedrock's, 2.04x.

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 . 3 of the 10 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Anthropic at 97.29% on 13 Nov 2026, Azure (azure/us) at 97.29% on 13 Nov 2026, and Azure (azure/global) at 97.74% on 13 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 · 5 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. reasoning_effortevery seller
  5. response_formatevery seller
  6. stopevery seller
  7. tool_choiceevery seller
  8. toolsevery seller
  9. verbosityevery seller
  10. structured_outputs3 of 5not Amazon Bedrock and Claude Platform on AWS
  11. max_completion_tokens1 of 5only Azure

9 of these 11 are accepted by every one of the 5 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 models

Blended $2.00 per million tokens, 3 in to 1 out: cheaper than 99 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 board

Each 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.

Intelligence Index54.5Position 6 of 58, above 90% of the models scored.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. Android native · Agents1260 Elowin rate 57.8% · source rank 6the board, 41 ranked
  2. blender3d · Agents1237 Elowin rate 60.1% · source rank 3the board, 25 ranked
  3. codetovideo · Agents1327 Elowin rate 70.2% · source rank 3the board, 26 ranked
  4. Mobile apps · Agents1259 Elowin rate 57.6% · source rank 6the board, 49 ranked
  5. pdf · Agents1247 Elowin rate 58.6% · source rank 11the board, 36 ranked
  6. spreadsheet · Agents1253 Elowin rate 46.3% · source rank 10the board, 32 ranked
  7. Web apps · Agents1297 Elowin rate 58.7% · source rank 4the board, 47 ranked
  8. 3D scenes · Models1403 Elowin rate 55.5% · source rank 8the board, 113 ranked
  9. Code · Models1343 Elowin rate 55.6% · source rank 8the board, 120 ranked
  10. Data visualisation · Models1362 Elowin rate 64.8% · source rank 3the board, 110 ranked
  11. Game development · Models1383 Elowin rate 58.4% · source rank 6the board, 120 ranked
  12. SVG · Models1300 Elowin rate 56.0% · source rank 8the board, 83 ranked
  13. UI components · Models1387 Elowin rate 63.6% · source rank 2the board, 116 ranked
  14. Websites · Models1306 Elowin rate 53.1% · source rank 13the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index166.6163.9 to 169.6
Position10 of 258above 96% of the models placed
Results behind it20benchmark results
As Epoch names itClaude Sonnet 5.5released 28 Sep 2026

Position 10 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 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Claude Sonnet 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.

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.
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.