Claude Opus 4.5
Anthropic · released Nov 24, 2025
- Type
- Closed
- Input
- $5.00
- Output
- $25.00
- Cached
- $0.50
List price · per 1M tokens · Anthropic at 200K context · machine-readable source ↗
Our take
Written Sep 1, 2026Claude Opus 4.5 is Anthropic's flagship reasoning model, available only through hosted APIs. It handles up to 200,000 tokens in a single request and accepts images and files alongside text, with strong measured scores in mathematics and coding.
Choose this for high-stakes reasoning and mathematics, long-context work up to 200,000 tokens, or coding where Arena Coding 1522.68 and SWE-bench Verified 79.2% matter. Skip it if you need agentic coding — its score there is roughly half its standard mark — or if instruction-following must match its other capabilities.
The case for it
- Strong measured mathematics performance: 90.39% on LiveBench Mathematics, its highest sub-score.
- Solid coding credentials across multiple benchmarks: LiveBench Coding 79.65%, Arena Coding 1522.68, SWE-bench Verified 79.2%.
- Broad multimodal input with very long context: 200,000-token request limit, accepts text, images and files.
- Highest throughput on major cloud providers: 78–79 tps on Claude-on-AWS and one Azure tier, versus 29–50 tps elsewhere.
The case against it
- Agentic coding drops sharply versus its own standard coding: 39.7% versus 79.65% on LiveBench.
- Instruction following is its weakest skill: 62.55% on LiveBench, 27.84 points below its Mathematics score.
- Premium pricing with almost no competition between hosts.
How good is it?
A closed text model from Anthropic for everyday questions, drafting and coding.
- getting answers to everyday questionsArena Text (overall) · 30th of 168
- drafts, rewrites and editingArena Creative Writing · 17th of 168
- writing and completing codeArena Coding · 20th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)30th of 168 · 1470
Also on this board: 1474 (Sep 25, 2026), 1473 (Aug 10, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding20th of 168 · 1523
Also on this board: 1531 (Sep 25, 2026), 1530 (Aug 10, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on LiveBench Agentic Coding, in 54th of 58 with 39.7.
WritingDrafting and rewriting prose
Arena Creative Writing17th of 168 · 1461
Also on this board: 1469 (Sep 25, 2026), 1469 (Aug 10, 2026). Read the pair, not the higher one.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model16 scoresEvery figure we hold, from 16 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 3 hours 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 200K of context.
- per 1M tokens
- $5.00 in / $25.00 out
- Context served
- 200K
- Throughput
- ~28 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| AnthropicDirect | $5.00 / $25.00checked 3 hours ago | 200K64K max reply | 28 tok/s | No | Yes30 days | Unknown |
| Microsoft Azure AIglobalThrough OpenRouter | $5.00 / $25.00checked 3 hours ago | 200K64K max reply | 25 tok/s | No | No | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $5.00 / $25.00checked 3 hours ago | 200K64K max reply | 55 tok/s | No | No | Confirmed |
| OpenRouterOpenRouter's own listing | $5.00 / $25.00checked 3 hours ago | 200K | not measured | Unknown | Unknown | Unknown |
| Amazon BedrockThrough OpenRouter | $5.00 / $25.00checked 3 hours ago | 200K64K max reply | 62 tok/s | No | No | Confirmed |
| Claude Platform on AWSThrough OpenRouter | $5.00 / $25.00checked 3 hours ago | 200K64K max reply | 17 tok/s | No | Yes30 days | Unknown |
| Amazon Bedrockeu-west-1Through OpenRouter | $5.50 / $27.50checked 3 hours ago | 200K64K max reply | 22 tok/s | No | No | Confirmed |
Microsoft Azure AI
Google Vertex AI
OpenRouter
Amazon BedrockAcross the 7 listings we hold: 6 say they do not train on prompts, 0 say they do and 1 does not say. 3 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 |
|---|---|---|---|
| AnthropicDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✗ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Amazon BedrockThrough OpenRouter | ✓ | ✓ | ✓ |
| Claude Platform on AWSThrough OpenRouter | ✓ | ✓ | ✓ |
| Amazon Bedrockeu-west-1Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 7 of 7 listings say yes. JSON output: 6 of 7 listings say yes, 1 says no. Strict schema: 7 of 7 listings say yes.
Models people weigh against Claude Opus 4.5
When we formed this view
Recent changes
What moved
first indexed by our pipelineWhat moved
leaderboardEach 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
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 7 listings does not say whether it trains 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-4-5