Claude Opus 4.7
Anthropic · released Apr 16, 2026
- Type
- Closed
- Input
- $5.00
- Output
- $25.00
- Cached
- $0.50
List price · per 1M tokens · Anthropic at 1M context · machine-readable source ↗
Our take
Written Sep 17, 2026Claude Opus 4.7 is a hosted-only model from Anthropic, so using it means choosing a host rather than running it yourself. Its measured strength is set-piece reasoning and maths; agentic work in an existing codebase is where it measures weakest.
Reach for it on hard maths, reasoning and self-contained coding problems where you want the strongest measured result and are paying per token through a host, or for long documents that would otherwise have to be split before sending. Pictures and files go in with the question. Skip it if you need an agent that reliably finishes a multi-step task or picks the right tool on its own, or if you meant to run the model on your own hardware.
The case for it
- Among the strongest measured results we hold on competition-style maths: 92.85% on LiveBench Mathematics, which covers olympiad problems rather than applied arithmetic.
- 87.19% on LiveBench Reasoning and 82.09% on LiveBench Coding, the latter covering generating and completing code rather than fixing issues in an existing project.
- Long inputs need not be broken up first, though reliable recall across the whole of a document is unverified in our data.
- Text, image and file input with written output, so a screenshot or a document does not have to be transcribed into words first.
The case against it
- Agentic work is its weakest measured area: 50.66% on LiveBench Agentic Coding inside an agent harness, with low agent-session scores on finishing the task and calling the right tool.
- Instruction following is among its weaker LiveBench categories at 66.74%, against 92.85% on its maths tasks.
- We list no download for it, so you cannot run it yourself and every route to it is a paid hosted offer.
How good is it?
A text model for everyday questions, writing and coding, and for multi-step work where it calls tools and changes course on request.
- getting answers to everyday questionsArena Text (overall) · 6th of 168
- drafts, rewrites and editingArena Creative Writing · 5th of 168
- writing and completing codeArena Coding · 4th of 168
- multi-step work it carries out for youArena Agent · 7th of 55
- calling tools to carry out requestsArena Agent · Tool use · 6th of 55
- changing course when you give new instructionsArena Agent · Steerability · 7th of 55
- getting back on track after a step failsArena Agent · Recovery · 7th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)6th of 168 · 1495
Also on this board: 1502 (Sep 25, 2026), 1502 (Aug 10, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding4th of 168 · 1547
Also on this board: 1551 (Sep 25, 2026), 1551 (Aug 10, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Arena Agent7th of 55 · 0.057
Also on this board: 0.06 (Sep 5, 2026), 0.082 (Aug 11, 2026). Read the pair, not the higher one.
WritingDrafting and rewriting prose
Arena Creative Writing5th of 168 · 1484
Also on this board: 1488 (Sep 25, 2026), 1490 (Aug 10, 2026). Read the pair, not the higher one.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked between 57 min and 60 min ago — each listing carries its own date.
Anthropic, direct
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Anthropic on 1M of context.
- per 1M tokens
- $5.00 in / $25.00 out
- Context served
- 1M
- Throughput
- ~41 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $5.00 / $25.00checked 60 min ago | 1M | not measured | Unknown | Unknown | Unknown |
| DeepInfraDirect | $5.00 / $25.00checked 59 min ago | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIglobalThrough OpenRouter | $5.00 / $25.00checked 59 min ago | 1M128K max reply | 41 tok/s | No | No | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $5.00 / $25.00checked 59 min ago | 1M128K max reply | 59 tok/s | No | No | Confirmed |
| AnthropicDirect | $5.00 / $25.00checked 57 min ago | 1M128K max reply | 41 tok/s | No | Yes30 days | Unknown |
| Amazon BedrockglobalThrough OpenRouter | $5.00 / $25.00checked 59 min ago | 1M128K max reply | 59 tok/s | No | No | Confirmed |
| Claude Platform on AWSThrough OpenRouter | $5.00 / $25.00checked 59 min ago | 1M128K max reply | 44 tok/s | No | Yes30 days | Unknown |
| Google Vertex AIeuropeThrough OpenRouter | $5.50 / $27.50checked 59 min ago | 1M128K max reply | 62 tok/s | No | No | Confirmed |
| Google Vertex AIusThrough OpenRouter | $5.50 / $27.50checked 59 min ago | 1M128K max reply | 62 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1Through OpenRouter | $5.50 / $27.50checked 59 min ago | 1M128K max reply | 60 tok/s | No | No | Confirmed |
OpenRouter
DeepInfra
Microsoft Azure AI
Google Vertex AI
Amazon BedrockAcross the 10 listings we hold: 8 say they do not train on prompts, 0 say they do and 2 do not say. 5 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfraDirect | |||
| Microsoft Azure AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| AnthropicDirect | ✓ | ✓ | ✓ |
| Amazon BedrockglobalThrough OpenRouter | ✓ | ✓ | ✗ |
| Claude Platform on AWSThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIeuropeThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIusThrough OpenRouter | ✓ | ✓ | ✓ |
| Amazon Bedrockeu-west-1Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 9 of 10 listings say yes, 1 publishes no parameter list. JSON output: 9 of 10 listings say yes, 1 publishes no parameter list. Strict schema: 7 of 10 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against Claude Opus 4.7
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- 1 of 10 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 10 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- anthropic-claude-opus-4-7