Claude Sonnet 5.5
Anthropic · released Sep 28, 2026
- Type
- Closed
- Input
- $2.00
- Output
- $10.00
- Cached
- $0.20
List price · per 1M tokens · Anthropic at 1M context · machine-readable source ↗
Our take
Written Sep 30, 2026Claude Sonnet 5.5 is a hosted-only model: we list no download for it, so using it means choosing a host. Its measured strength is set-piece coding and mathematics, where it places at the top of the LiveBench field, and it takes text, images and files in one request.
Reach for it on set-piece code generation and competition-style mathematics, where it places 1st of 58 on LiveBench Coding via Max effort as of 25 Jun 2026, and for long documents that would otherwise have to be split before being sent. Nine hosted offers across six companies mean you can move the workload if a host changes its terms. Skip it if you need fixes landed inside an existing codebase without review, or if you meant to run the model on your own machine.
The case for it
- 1st of 58 on LiveBench Coding via Max effort as of 25 Jun 2026, a board of code generation and completion exercises rather than fixing issues in an existing project.
- 4th of 58 on LiveBench Mathematics via xHigh effort as of 25 Jun 2026, covering competition and olympiad maths problems.
- Long documents go in whole rather than being split first, though reliable recall across all of it is unverified in our data.
- Text, images and files go into the same request, so a screenshot or a document does not have to be described in words first.
The case against it
- 22nd of 58 on LiveBench Agentic Coding via Max effort as of 25 Jun 2026, and that figure is a result for the model inside an agent harness rather than for the model on its own.
- 24th of 58 on LiveBench Instruction Following via xHigh effort as of 25 Jun 2026, over constrained-rewriting tasks.
- We list no download for it, so every route runs through a host and that host's terms.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on LiveBench Mathematics, in 4th of 58 with 96.69.
CodingWriting and fixing code on its own
Not yet scored on Arena Coding. It is on LiveBench Coding, in 1st of 58 with 91.37.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on LiveBench Agentic Coding, in 22nd of 58 with 56.31.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing. It is on LiveBench Language, in 16th of 58 with 83.43.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model8 scoresEvery figure we hold, from 8 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 4 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 1M of context.
- per 1M tokens
- $2.00 in / $10.00 out
- Context served
- 1M
- Throughput
- ~84 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $10.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| DeepInfraDirect | $2.00 / $10.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIglobalThrough OpenRouter | $2.00 / $10.00checked 4 hours ago | 1M128K max reply | 93 tok/s | No | No | Unknown |
| AnthropicDirect | $2.00 / $10.00checked 4 hours ago | 1M128K max reply | 84 tok/s | No | Yes30 days | Unknown |
| Amazon BedrockThrough OpenRouter | $2.00 / $10.00checked 4 hours ago | 1M128K max reply | 98 tok/s | No | No | Confirmed |
| Claude Platform on AWSThrough OpenRouter | $2.00 / $10.00checked 4 hours ago | 1M128K max reply | 79 tok/s | No | Yes30 days | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $2.00 / $10.00checked 4 hours ago | 1M128K max reply | 94 tok/s | No | No | Confirmed |
| Microsoft Azure AIusThrough OpenRouter | $2.20 / $11.00checked 4 hours ago | 1M128K max reply | 55 tok/s | No | No | Unknown |
| Google Vertex AIeuropeThrough OpenRouter | $2.20 / $11.00checked 4 hours ago | 1M128K max reply | 81 tok/s | No | No | Confirmed |
| Google Vertex AIusThrough OpenRouter | $2.20 / $11.00checked 4 hours ago | 1M128K max reply | 77 tok/s | No | No | Confirmed |
OpenRouter
DeepInfra
Microsoft Azure AI
Amazon Bedrock
Google Vertex AIAcross the 10 listings we hold: 8 say they do not train on prompts, 0 say they do and 2 do not say. 4 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 | ✓ | ✓ | ✓ |
| AnthropicDirect | ✓ | ✓ | ✓ |
| Amazon BedrockThrough OpenRouter | ✓ | ✓ | ✗ |
| Claude Platform on AWSThrough OpenRouter | ✓ | ✓ | ✗ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIusThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIeuropeThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIusThrough 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 Sonnet 5.5
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
- 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-sonnet-5-5