Get started

Claude Sonnet 4.5 (batch)

Timed at 44.7 tok/s, scored 52.1 on the Coding Index, and on 11 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Sonnet 4.5 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-sonnet-4.5: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$1.50per 1M tokens
Output$7.50per 1M tokens
Cached input$0.15per 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$1.875per 1M tokens
Cache write, 1 hour$3.00per 1M tokens
Web search$0.01per search
Over the base window · the rate the list gives once a prompt is longer than a thresholdin / out per 1M tokens
Prompts over 200K tokens$3.00 / $11.25cached $0.30
What the list says · the fields OpenRouter publishes for this id12 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-4.5-sonnet-20250929
Context1,000,000 tokens
Max output64,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional
Moderationmoderated by OpenRouter
Variantbatch
Knowledge cutoff2025-01-31
Other listingbase listing

Measured speed

13,657 requests · 6 endpoints · 30-minute window
Throughput44.7 tok/sMedian output rate, weighted across the 6 endpoints serving it by the requests each answered.the speed board
First token1.01sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread35 to 59The 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

6 priced · 6 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock$3.00$15.00$0.30not declared64k59 tok/s511.44s98 req100%
  2. Amazon Bedrockamazon-bedrock$3.00$15.00$0.30not declared64k49 tok/s38990ms5,296 req100%
  3. Anthropicanthropic$3.00$15.00$0.30not declared64k40 tok/s281s985 req100%
  4. Azureazure/global$3.00$15.00$0.30not declared64k43 tok/s281.94s10 reqno reading
  5. Claude Platform on AWSclaude-on-aws$3.00$15.00$0.30not declared64k42 tok/s311.03s7,234 req100%
  6. Googlegoogle-vertex/global$3.00$15.00$0.30not declared64k35 tok/s30823ms34 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: 4 of the 6 timed routes are slower than it, and the middle route runs at 42.5 tok/s. The widest median-to-p90 gap is Azure's, 1.54x.

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 7 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Amazon Bedrock (amazon-bedrock/eu-west-1) at 72.22% on 17 Nov 2026, Anthropic at 97.84% on 13 Nov 2026, and Google (google-vertex/global) at 97.95% 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

12 parameters · 5 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. structured_outputsevery seller
  5. temperatureevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. top_kevery seller
  9. top_pevery seller
  10. response_format4 of 5not Google
  11. stop4 of 5not Azure
  12. max_completion_tokens1 of 5only Azure

9 of these 12 are accepted by every one of the 5 sellers that publish a list; the other 3 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 $3.00 per million tokens, 3 in to 1 out: cheaper than 81 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 Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index52.1Position 53 of 118, above 54% of the models scored.the coding leaderboard
Agentic Index15.8Position 50 of 94, above 46% of the models scored.the agentic leaderboard
  1. Full stack · Agents1024 Elowin rate 43.7% · source rank 38the board, 44 ranked
  2. Mobile apps · Agents1129 Elowin rate 53.0% · source rank 38the board, 49 ranked
  3. Web apps · Agents1040 Elowin rate 43.2% · source rank 43the board, 47 ranked
  4. 3D scenes · Models1137 Elowin rate 51.0% · source rank 76the board, 113 ranked
  5. ASCII art · Models1188 Elowin rate 56.1% · source rank 28the board, 67 ranked
  6. Code · Models1171 Elowin rate 51.5% · source rank 71the board, 120 ranked
  7. Data visualisation · Models1163 Elowin rate 47.4% · source rank 74the board, 110 ranked
  8. Game development · Models1155 Elowin rate 51.1% · source rank 75the board, 120 ranked
  9. SVG · Models1104 Elowin rate 52.2% · source rank 66the board, 83 ranked
  10. UI components · Models1161 Elowin rate 49.4% · source rank 76the board, 116 ranked
  11. Websites · Models1180 Elowin rate 51.8% · source rank 77the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index147.6146.1 to 149.1
Position82 of 258above 68% of the models placed
Results behind it26benchmark results
As Epoch names itClaude Sonnet 4.5released 29 Sep 2025

Position 82 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 4.5 (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.