Claude Opus 4.6
Anthropic · released Feb 4, 2026
- Type
- Proprietary
- Input
- $5.00
- Output
- $25.00
- Cached
- $0.50
List price · per 1M tokens · Anthropic at 1M context · source ↗
Our take
Written Aug 3, 2026Claude Opus 4.6 is Anthropic's flagship hosted-only reasoning model with a one-million-token request limit and top scores on the independent coding and hard-prompt leaderboards we track. It is built for demanding long-document and coding work, but costs noticeably more than most alternatives and cannot be downloaded or fine-tuned.
Pick this for highest-stakes coding and reasoning where its leaderboard scores justify the premium, or for very long documents needing the widest context window we track. Use it if your enterprise is already on Anthropic, Amazon Bedrock, Azure, OpenRouter or Google Vertex. Skip it if budget matters more than marginal quality gains, if you need consistent throughput, or if you require downloadable weights.
The case for it
- One-million-token request limit, the widest in our data.
- Top-quartile coding performance on the Arena leaderboard.
- Strong hard-prompt reasoning score on the same leaderboard.
- Available on five enterprise providers, giving deployment flexibility.
The case against it
- Premium pricing with no budget tier in its family.
- Throughput varies sharply by provider: a 64% gap between fastest and slowest measured host.
- No open weights or fine-tuning access; proprietary licence terms are undisclosed.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)2nd of 143 · 1497.2
Also on this board: 1505.4 via Thinking (Aug 2, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding2nd of 143 · 1547.9
Also on this board: 1551.1 via Thinking (Aug 2, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)8th of 36 · 0.065
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 4.6 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 model17 scoresEvery figure we hold, from 17 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
- 1M
- Throughput
- ~30 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Amazon Bedrockus-east-1 | $5.00 / $25.00 | 1M | 36 tok/s | No | No | Confirmed |
| Microsoft Azure AIglobal | $5.00 / $25.00 | 1M | 30 tok/s | No | No | Unknown |
| Microsoft Azure AIus-east-2 | $5.00 / $25.00 | 1M | 23 tok/s | No | No | Unknown |
| OpenRouter | $5.00 / $25.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIglobal | $5.00 / $25.00 | 1M | 37 tok/s | No | No | Confirmed |
| Anthropic | $5.00 / $25.00 | 1M128K out | 35 tok/s | No | Yes30 days | Unknown |
| Google Vertex AIeurope | $5.50 / $27.50 | 1M | 36 tok/s | No | No | Confirmed |
Amazon Bedrock
OpenRouter
Google Vertex AIAcross 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 |
|---|---|---|---|
| Amazon Bedrockus-east-1 | ✓ | ✓ | ✓ |
| Microsoft Azure AIglobal | ✓ | ✓ | ✓ |
| Microsoft Azure AIus-east-2 | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✓ | ✓ | ✗ |
| Anthropic | ✓ | ✓ | ✓ |
| Google Vertex AIeurope | ✓ | ✓ | ✗ |
Tool calling: 7 of 7 listings say yes. JSON output: 7 of 7 listings say yes. Strict schema: 5 of 7 listings say yes, 2 say no.
Models people weigh against Claude Opus 4.6
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-4-6