Get started

Claude Sonnet 5

Timed at 73.6 tok/s, scored 71.5 on the Coding Index, on 20 Design Arena boards, and with results on 2 openly licensed boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Sonnet 5USD per 1M tokens · as OpenRouter routes it
anthropic/claude-sonnet-5Anthropic · base listing · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$2.00per 1M tokens
Output$10.00per 1M tokens
Cached input$0.20per 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$2.50per 1M tokens
Cache write, 1 hour$4.00per 1M tokens
Web search$0.01per search
What Vitna read · 2 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
DeepInfraresold$3.00 / $15.00confirmed 22 Nov 2026
Anthropicthe maker$2.00 / $10.00confirmed 22 Nov 2026

The same model sold by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.

What the list says · the fields OpenRouter publishes for this id10 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-sonnet-5-20260630
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional, on by default · effort max, xhigh, high, medium, low, none, high by default
Moderationmoderated by OpenRouter
Other listingbatch variant

Measured speed

20,964 requests · 7 endpoints · 30-minute window
Throughput73.6 tok/sMedian output rate, weighted across the 7 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 spread65 to 101The 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

7 priced · 7 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock/global · listed$2.00$10.00$0.20not declared128k76 tok/s48993ms16 req100%
  2. Amazon Bedrockamazon-bedrock/global · listed$2.00$10.00$0.20not declared128k65 tok/s431.13s3,126 req100%
  3. Anthropicanthropic · listed$2.00$10.00$0.20not declared128k74 tok/s46915ms3,419 req100%
  4. Azureazure/global · listed$2.00$10.00$0.20not declared128k80 tok/s37.72.88s3 req100%
  5. Claude Platform on AWSclaude-on-aws · listed$2.00$10.00$0.20not declared128k73 tok/s49964ms12,245 req100%
  6. Googlegoogle-vertex/global · listed$2.00$10.00$0.20not declared128k86 tok/s60.11.24s1,719 req100%
  7. Googlegoogle-vertex/global · listed$2.00$10.00$0.20not declared128k101 tok/s841.4s436 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 7 timed routes are slower than it, and the middle route runs at 76 tok/s. The widest median-to-p90 gap is Azure's, 2.12x.

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 10 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Azure (azure/global) at 48.38% on 13 Nov 2026, Google (google-vertex/europe) at 95.57% on 10 Nov 2026, Amazon Bedrock (amazon-bedrock/global) at 96.66% on 9 Nov 2026, Anthropic at 97.15% 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 · 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_outputs4 of 5not Amazon Bedrock
  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 $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 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 Index71.5Position 20 of 118, above 82% of the models scored.the coding leaderboard
Agentic Index43.6Position 14 of 94, above 85% of the models scored.the agentic leaderboard
  1. Agentic game development · Agents1169 Elowin rate 51.6% · source rank 8the board, 25 ranked
  2. Android native · Agents1210 Elowin rate 53.0% · source rank 12the board, 41 ranked
  3. blender3d · Agents956 Elowin rate 31.2% · source rank 23the board, 25 ranked
  4. codetovideo · Agents1123 Elowin rate 42.6% · source rank 22the board, 26 ranked
  5. Full stack · Agents1224 Elowin rate 53.3% · source rank 12the board, 44 ranked
  6. Godot game development · Agents1191 Elowin rate 53.8% · source rank 14the board, 34 ranked
  7. HTML slides · Agents1113 Elowin rate 53.7% · source rank 9the board, 25 ranked
  8. Mobile apps · Agents1201 Elowin rate 50.1% · source rank 21the board, 49 ranked
  9. pdf · Agents1220 Elowin rate 54.8% · source rank 15the board, 36 ranked
  10. python-pptx slides · Agents1179 Elowin rate 48.1% · source rank 15the board, 29 ranked
  11. spreadsheet · Agents1033 Elowin rate 25.6% · source rank 22the board, 32 ranked
  12. Web apps · Agents1222 Elowin rate 51.8% · source rank 16the board, 47 ranked
  13. 3D scenes · Models1237 Elowin rate 52.8% · source rank 35the board, 113 ranked
  14. ASCII art · Models1189 Elowin rate 50.8% · source rank 27the board, 67 ranked
  15. Code · Models1266 Elowin rate 52.5% · source rank 28the board, 120 ranked
  16. Data visualisation · Models1247 Elowin rate 52.7% · source rank 36the board, 110 ranked
  17. Game development · Models1272 Elowin rate 51.4% · source rank 26the board, 120 ranked
  18. SVG · Models1183 Elowin rate 48.8% · source rank 38the board, 83 ranked
  19. UI components · Models1265 Elowin rate 53.4% · source rank 35the board, 116 ranked
  20. Websites · Models1267 Elowin rate 52.5% · source rank 30the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index156.9154.9 to 159.1
Position36 of 258above 86% of the models placed
Results behind it18benchmark results
As Epoch names itClaude Sonnet 5released 30 Jun 2026

Position 36 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

2 of 6 boards · 36 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.08 of 22 tasks

Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names these runs claude-sonnet-5_max, claude-sonnet-5_xhigh and claude-sonnet-5, and the effort beside each score says which run it is, unstated where the publisher wrote none. A run missing from a task's rows has no published result there, which is not a score of zero. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

LiveBench · publisher-run, Apache-2.023 of 23 tasks · 71 runs scored on each task · at xhigh effort

Percent correct on the task the row names, higher is better. All 23 published columns; there is no average to carry, because the site computes its headline in the browser from a weighting this does not reimplement. LiveBench names this run claude-sonnet-5-xhigh-effort. Read from livebench.ai ↗, which dates its own data . LiveBench, Apache-2.0. Results produced by the LiveBench maintainers on questions refreshed monthly.

2 of the 6 openly licensed boards Vitna mirrors carry a result for Claude Sonnet 5, each printed as its publisher published it and none added to another. MTEB, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. 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.