Get started

Claude Opus 4.8 (batch)

Sold by 6 sellers, timed at 53.5 tok/s, scored 74.3 on the Coding Index, and on 25 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Opus 4.8 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-opus-4.8: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-4.8-opus-20260528
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional, off by default · effort max, xhigh, high, medium, low, none, high by default
Moderationmoderated by OpenRouter
Variantbatch
Other listingbase listing

What sellers charge

6 sellers · 2x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $5.00 at Amazon Bedrock to $10.00 at Anthropic. The $2.50 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

3,272 requests · 8 endpoints · 30-minute window
Throughput53.5 tok/sMedian output rate, weighted across the 8 endpoints serving it by the requests each answered.the speed board
First token935msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread41 to 104The 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

8 priced · 8 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock$5.00$25.00$0.50not declared128k78.5 tok/s53.5569ms3 req99.89%
  2. Amazon Bedrockamazon-bedrock$5.00$25.00$0.50not declared128k66.5 tok/s442.76s296 req99.89%
  3. Anthropicanthropic$5.00$25.00$0.50not declared128knot matchednonenonenot matched100%
  4. Azureazure/global$5.00$25.00$0.50not declared128k61.5 tok/s40.32.99s4 reqno reading
  5. Claude Platform on AWSclaude-on-aws$5.00$25.00$0.50not declared128k57 tok/s30695ms1,942 req100%
  6. Googlegoogle-vertex/global$5.00$25.00$0.50not declared128k77 tok/s64444ms4 req100%
  7. Googlegoogle-vertex/global$5.00$25.00$0.50not declared128k84 tok/s55985ms23 req100%
  8. Anthropicanthropic/fast$10.00$50.00$1.00not declared128knot matchednonenonenot matched100%
  9. Anthropicnot matchednot matchednot matchednot matchedno offer104 tok/s79505ms15 reqno offer
  10. Anthropicnot matchednot matchednot matchednot matchedno offer41 tok/s28.6861ms985 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: 1 of the 8 timed routes are slower than it, and the middle route runs at 71.8 tok/s. The widest median-to-p90 gap is Claude Platform on AWS's, 1.9x.

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 . 5 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: Amazon Bedrock (amazon-bedrock) at 87.63% on 11 Nov 2026, Amazon Bedrock (amazon-bedrock/us) at 93.08% on 11 Nov 2026, Amazon Bedrock (amazon-bedrock/eu-west-1) at 94.44% on 9 Nov 2026, Anthropic (anthropic) at 97.26% on 13 Nov 2026, and 1 more. 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
  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_outputs5 of 6not Amazon Bedrock
  11. 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 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 Index74.3Position 14 of 118, above 88% of the models scored.the coding leaderboard
Agentic Index41.9Position 18 of 94, above 81% of the models scored.the agentic leaderboard
  1. Agentic game development · Agents1182 Elowin rate 55.3% · source rank 5the board, 25 ranked
  2. Agentic HTML slides · Agents1227 Elowin rate 55.6% · source rank 3the board, 9 ranked
  3. Agentic slides · Agents1294 Elowin rate 64.8% · source rank 1the board, 9 ranked
  4. Agentic slides, HTML · Agents1230 Elowin rate 56.0% · source rank 3the board, 9 ranked
  5. Agentic slides, python-pptx · Agents1310 Elowin rate 68.9% · source rank 1the board, 9 ranked
  6. Android native · Agents1222 Elowin rate 55.9% · source rank 11the board, 41 ranked
  7. blender3d · Agents1096 Elowin rate 48.2% · source rank 13the board, 25 ranked
  8. codetovideo · Agents1206 Elowin rate 54.4% · source rank 12the board, 26 ranked
  9. Full stack · Agents1224 Elowin rate 55.1% · source rank 11the board, 44 ranked
  10. Godot game development · Agents1202 Elowin rate 55.8% · source rank 11the board, 34 ranked
  11. HTML slides · Agents1118 Elowin rate 58.1% · source rank 8the board, 25 ranked
  12. Mobile apps · Agents1207 Elowin rate 53.5% · source rank 18the board, 49 ranked
  13. pdf · Agents1175 Elowin rate 50.3% · source rank 22the board, 36 ranked
  14. PPTX slides · Agents1306 Elowin rate 67.9% · source rank 1the board, 8 ranked
  15. python-pptx slides · Agents1298 Elowin rate 65.9% · source rank 2the board, 29 ranked
  16. spreadsheet · Agents1039 Elowin rate 23.0% · source rank 21the board, 32 ranked
  17. Web apps · Agents1213 Elowin rate 50.3% · source rank 18the board, 47 ranked
  18. 3D scenes · Models1202 Elowin rate 51.0% · source rank 50the board, 113 ranked
  19. ASCII art · Models1260 Elowin rate 61.3% · source rank 11the board, 67 ranked
  20. Code · Models1242 Elowin rate 52.1% · source rank 45the board, 120 ranked
  21. Data visualisation · Models1234 Elowin rate 52.5% · source rank 42the board, 110 ranked
  22. Game development · Models1250 Elowin rate 51.8% · source rank 38the board, 120 ranked
  23. SVG · Models1181 Elowin rate 50.4% · source rank 39the board, 83 ranked
  24. UI components · Models1245 Elowin rate 52.7% · source rank 46the board, 116 ranked
  25. Websites · Models1249 Elowin rate 52.8% · source rank 44the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index159.9157.8 to 162.2
Position23 of 258above 91% of the models placed
Results behind it26benchmark results
As Epoch names itClaude Opus 4.8released 28 May 2026

Position 23 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 4.8 (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.