Claude Opus 4.5
Anthropic · released Nov 24, 2025
- Type
- Proprietary
- Input
- $5.00
- Output
- $25.00
- Cached
- $0.50
List price · per 1M tokens · Anthropic at 200K context · source ↗
Our take
Written Aug 2, 2026Claude Opus 4.5 is Anthropic's flagship reasoning model, available only through hosted APIs with a 200,000-token request limit. It excels at complex coding and difficult prompts, though its creative writing and maths scores sit noticeably below those peaks.
Choose this for complex coding tasks where its Arena Coding Elo of 1530.2 is the headline strength, or for hard prompts and adversarial instructions at 1499.4. Use it for long-document analysis with its 200,000-token context, or when you need multimodal inputs combining text, images and files. Skip it if you are on a tight budget, need guaranteed fast throughput, or want strong creative writing from the same model.
The case for it
- Arena Coding Elo of 1530.2, with a confirming second run at 1522.6.
- Arena Hard Prompts Elo of 1499.4 on deliberately difficult instructions.
- 200,000-token context window for long-form document work.
- Consistent premium pricing across most providers, with no undercutting.
The case against it
- Creative writing Elo of 1460.2 lags 70 points behind its own coding peak.
- Maths Elo of 1469.3 trails its hard-prompt and coding scores by 30–61 points.
- Premium pricing with no budget tier; throughput varies from 29 to 58 tokens per second with no guaranteed floor.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)19th of 143 · 1468.9
Also on this board: 1472.8 via Thinking 32k (Aug 2, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding11th of 143 · 1523
Also on this board: 1530 via Thinking 32k (Aug 2, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Claude Opus 4.5 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 1st of 39 with 79.2.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Claude Opus 4.5 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
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.
Or rent it from someone else
Why this differs from the header. The strip above quotes Anthropic's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $5.00 in / $25.00 out
- Context served
- 200K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $5.00 / $25.00 | 200K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIglobal | $5.00 / $25.00 | 200K | 51 tok/s | No | No | Unknown |
| Microsoft Azure AIus-east-2 | $5.00 / $25.00 | 200K | 29 tok/s | No | No | Unknown |
| Google Vertex AIglobal | $5.00 / $25.00 | 200K | 43 tok/s | No | No | Confirmed |
| Anthropic | $5.00 / $25.00 | 200K64K out | 42 tok/s | No | Yes30 days | Unknown |
| Amazon Bedrock | $5.00 / $25.00 | 200K | 36 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1 | $5.50 / $27.50 | 200K | 3 tok/s | No | No | Confirmed |
Microsoft Azure AI
Google Vertex AI
Amazon BedrockAcross the 7 listings we hold: 6 say they do not train on prompts, 0 say they do and 1 do not say. 3 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIglobal | ✓ | ✓ | ✓ |
| Microsoft Azure AIus-east-2 | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✓ | ✗ | ✗ |
| Anthropic | ✓ | ✓ | ✓ |
| Amazon Bedrock | ✓ | ✓ | ✓ |
| Amazon Bedrockeu-west-1 | ✓ | ✓ | ✓ |
Tool calling: 7 of 7 listings say yes. JSON output: 6 of 7 listings say yes, 1 says no. Strict schema: 6 of 7 listings say yes, 1 says no.
Models people weigh against Claude Opus 4.5
When we formed this view
Dates behind this page
Prices last checked 9d ago
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 do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- anthropic-claude-opus-4-5