Get started

Claude Opus 4.6 (batch)

Timed at 37.3 tok/s, on 17 Design Arena boards, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Opus 4.6 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-opus-4.6: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$2.50per 1M tokens
Output$12.50per 1M tokens
Cached input$0.25per 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$3.125per 1M tokens
Cache write, 1 hour$5.00per 1M tokens
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-4.6-opus-20260205
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional, off by default · effort max, high, medium, low, none, high by default
Moderationmoderated by OpenRouter
Variantbatch
Other listingbase listing

Measured speed

4,065 requests · 5 endpoints · 30-minute window
Throughput37.3 tok/sMedian output rate, weighted across the 5 endpoints serving it by the requests each answered.the speed board
First token1.67sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread28 to 45The 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

5 priced · 5 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock$5.00$25.00$0.50not declared128k45 tok/s301.34s359 req99.42%
  2. Anthropicanthropic$5.00$25.00$0.50not declared128k31 tok/s221.89s1,160 req100%
  3. Azureazure/global$5.00$25.00$0.50not declared128k28 tok/s171.75s1 reqno reading
  4. Claude Platform on AWSclaude-on-aws$5.00$25.00$0.50not declared128k39 tok/s301.55s2,244 req100%
  5. Googlegoogle-vertex/global$5.00$25.00$0.50not declared128k39.5 tok/s292.03s301 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: 2 of the 5 timed routes are slower than it, and the middle route runs at 39 tok/s. The widest median-to-p90 gap is Azure's, 1.65x.

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 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Google (google-vertex/europe) at 88.88% on 7 Nov 2026, Google (google-vertex/global) at 95.83% on 18 Nov 2026, and Anthropic at 97.27% 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

14 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. structured_outputsevery seller
  8. temperatureevery seller
  9. tool_choiceevery seller
  10. toolsevery seller
  11. top_pevery seller
  12. verbosityevery seller
  13. top_k2 of 5not Anthropic, Claude Platform on AWS, and Google
  14. max_completion_tokens1 of 5only Azure

12 of these 14 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 $5.00 per million tokens, 3 in to 1 out: cheaper than 37 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 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. Agentic game development · Agents1143 Elowin rate 45.5% · source rank 11the board, 25 ranked
  2. Android native · Agents1180 Elowin rate 61.0% · source rank 18the board, 41 ranked
  3. blender3d · Agents1008 Elowin rate 37.2% · source rank 20the board, 25 ranked
  4. codetovideo · Agents1127 Elowin rate 43.8% · source rank 21the board, 26 ranked
  5. Full stack · Agents1194 Elowin rate 59.2% · source rank 16the board, 44 ranked
  6. Mobile apps · Agents1198 Elowin rate 57.1% · source rank 22the board, 49 ranked
  7. pdf · Agents1191 Elowin rate 51.4% · source rank 21the board, 36 ranked
  8. spreadsheet · Agents995 Elowin rate 22.5% · source rank 28the board, 32 ranked
  9. Web apps · Agents1186 Elowin rate 55.6% · source rank 26the board, 47 ranked
  10. 3D scenes · Models1254 Elowin rate 62.5% · source rank 26the board, 113 ranked
  11. ASCII art · Models1238 Elowin rate 61.9% · source rank 18the board, 67 ranked
  12. Code · Models1277 Elowin rate 61.2% · source rank 25the board, 120 ranked
  13. Data visualisation · Models1276 Elowin rate 58.7% · source rank 21the board, 110 ranked
  14. Game development · Models1267 Elowin rate 61.0% · source rank 27the board, 120 ranked
  15. SVG · Models1217 Elowin rate 60.9% · source rank 26the board, 83 ranked
  16. UI components · Models1272 Elowin rate 59.8% · source rank 31the board, 116 ranked
  17. Websites · Models1282 Elowin rate 61.1% · source rank 23the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index156.3154.6 to 158.3
Position40 of 258above 85% of the models placed
Results behind it27benchmark results
As Epoch names itClaude Opus 4.6released 5 Feb 2026

Position 40 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 Opus 4.6 (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.