Claude Opus 4.7 (batch)
Timed at 49.8 tok/s and scored 73.6 on the Coding Index.
retrieved sha256 · 0bb53a77713f
Measured speed
1,381 requests · 7 endpoints · 30-minute windowOpenRouter'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- Amazon Bedrockamazon-bedrock/global$5.00$25.00$0.50not declared128k58.5 tok/s45.5922ms142 req100%
- Amazon Bedrockamazon-bedrock/global$5.00$25.00$0.50not declared128k59.5 tok/s43.9784ms2 req100%
- Anthropicanthropic$5.00$25.00$0.50not declared128k45 tok/s29909ms150 req100%
- Azureazure/global$5.00$25.00$0.50not declared128k45.5 tok/s31.9685ms1 reqno reading
- Claude Platform on AWSclaude-on-aws$5.00$25.00$0.50not declared128k46 tok/s34908ms881 req100%
- Googlegoogle-vertex/global$5.00$25.00$0.50not declared128k63.5 tok/s52565ms200 req100%
- Googlegoogle-vertex/global$5.00$25.00$0.50not declared128k77 tok/s64444ms5 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: 3 of the 7 timed routes are slower than it, and the middle route runs at 58.5 tok/s. The widest median-to-p90 gap is Anthropic's, 1.55x.
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 . 2 of the 8 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 97.44% on 13 Nov 2026 and Amazon Bedrock (amazon-bedrock/global) at 98.58% on 10 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- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- tool_choiceevery seller
- toolsevery seller
- verbosityevery seller
- stop4 of 5not Azure
- structured_outputs4 of 5not Amazon Bedrock
- max_completion_tokens1 of 5only Azure
8 of these 11 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 modelsBlended $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 boardEach 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.
Not ranked in any Design Arena category.
Position 32 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 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for Claude Opus 4.7 (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.
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.
