What this read moved
26–43 of 43This capture is too large to show at once. Changes 26-43 of 43 are below, significant first; the rest are on the following screens.
manage-claude/compliance-sessions Changed · +2 / -2 lines
from line 44
4444| Infrastructure | Anthropic-hosted | Anthropic-hosted | You run the collector and storage |
4545| ID prefix | `clls_` | `cse_` | N/A |
4646| `product_surface` values | `cowork`, `claude_code`, `claude_science`, and values beginning with `office_agents` | `cowork_remote` | N/A |
47| Retention | 6 years by default, or your organization's custom conversation retention period when a finite one is set; held by Anthropic | 6 years, held by Anthropic | Your infrastructure, your policies |
47| Retention | 6 years by default, or your organization's custom conversation retention period when a finite one is set; held by Anthropic | 6 years, unless a user deletes the session sooner; held by Anthropic | Your infrastructure, your policies |
4848| User prompts and assistant responses | Yes | Yes | Yes, subject to content-capture settings |
4949| Tool inputs | Truncated to 10,000 bytes per input by default; up to about 1 MiB on request | Truncated to 10,000 bytes per input by default; up to about 1 MiB on request | Truncated summaries |
5050| Tool result content | Each text entry truncated to 10,000 bytes by default; up to about 1 MiB on request | Each text entry truncated to 10,000 bytes by default; up to about 1 MiB on request | Metadata such as size and success; Claude Code can also capture content with an optional, size-capped setting |
from line 418
418418
419419## Retention and deletion
420420
421The session endpoints are read-only; local and remote sessions cannot be deleted through the Compliance API. Local session transcripts are retained for 6 years by default, or your organization's custom conversation retention period when a finite one is set, as described under [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions). Remote session transcripts are retained for 6 years. To learn how these periods sit alongside Anthropic's other retention arrangements, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
421The session endpoints are read-only; local and remote sessions cannot be deleted through the Compliance API. Local session transcripts are retained for 6 years by default, or your organization's custom conversation retention period when a finite one is set, as described under [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions). Remote session transcripts are retained for 6 years, unless a user deletes the session sooner. The remote session endpoints no longer return a session once a user deletes it, and its transcript is not recoverable through the Compliance API. To learn how these periods sit alongside Anthropic's other retention arrangements, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
422422
423423## Next steps
424424
manage-claude/inference-hooks Changed · +1 / -1 lines
from line 60
6060
6161Inference hooks are available to Claude Enterprise organizations. Configuring them requires the `organization:manage` permission, which the built-in Admin, Owner, and Primary owner roles hold, as does any custom role granted it.
6262
63One hook governs conversations across claude.ai, Cowork, and Claude Code sessions in your Claude Enterprise organization, whether they run on the web, in the desktop app, or in the CLI. Inference hooks are not available on Amazon Bedrock or Google Cloud.
63One hook governs conversations across claude.ai, Cowork, and Claude Code sessions in your Claude Enterprise organization, whether they run on the web, in the desktop or mobile apps, or in the CLI. Inference hooks are not available on Amazon Bedrock or Google Cloud.
6464
6565Governed requests are the inference requests behind the user's conversation. Ancillary requests, such as conversation title generation, aren't sent to your endpoint, and system prompts and tool definitions are never included in what is sent. Voice mode is not covered.
6666
managed-agents/quickstart Changed · +2 / -2 lines
from line 37
3737 For Linux environments, download the release binary directly.
3838
3939 ```bash
40 VERSION=1.27.0
40 VERSION=1.29.0
4141 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
4242 case $(uname -m) in
4343 x86_64) ARCH=amd64 ;;
from line 88
8888
8989 <Tab title="Java">
9090 ```groovy Gradle
91 implementation("com.anthropic:anthropic-java:2.58.0")
91 implementation("com.anthropic:anthropic-java:2.60.0")
9292 ```
9393 </Tab>
9494
managed-agents/self-hosted-sandboxes Changed · +2 / -2 lines
from line 214
214214 For Linux environments, download the release binary directly.
215215
216216 ```bash
217 VERSION=1.27.0
217 VERSION=1.29.0
218218 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
219219 case $(uname -m) in
220220 x86_64) ARCH=amd64 ;;
from line 252
252252
253253 ```text
254254 FROM your-base-image
255 ARG ANT_VERSION=1.27.0
255 ARG ANT_VERSION=1.29.0
256256 ARG TARGETARCH
257257 RUN ARCH=$([ "$TARGETARCH" = "arm64" ] && echo arm64 || echo amd64) && \
258258 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${ANT_VERSION}/ant_${ANT_VERSION}_linux_${ARCH}.tar.gz" \
models/fable-5-1/overview Changed · +1 / -1 lines
from line 37
3737
3838* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3939* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
40* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
40* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
4141* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
4242* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
4343* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/fable-5/overview Changed · +1 / -1 lines
from line 30
3030
3131* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3232* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
33* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
33* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3434* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3535* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3636* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/haiku-4-5/overview Changed · +1 / -1 lines
from line 25
2525
2626* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2727* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
28* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
28* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
2929* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/mythos-5-1/overview Changed · +1 / -1 lines
from line 28
2828
2929* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3030* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
31* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
31* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3232* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3333* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3434* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/mythos-5/overview Changed · +1 / -1 lines
from line 28
2828
2929* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3030* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
31* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
31* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3232* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3333* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3434* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-5/overview Changed · +1 / -1 lines
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-6/overview Changed · +1 / -1 lines
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-7/overview Changed · +1 / -1 lines
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-8/overview Changed · +1 / -1 lines
from line 24
2424
2525* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2626* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
27* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
27* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
2828* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
2929* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3030* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-5/overview Changed · +1 / -1 lines
from line 31
3131
3232* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3333* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
34* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
34* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3535* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3636* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3737* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/overview Changed · +1 / -1 lines
from line 45
4545| [Claude Platform on AWS ID](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1` | — | `claude-sonnet-5` | `claude-haiku-4-5` |
4646
4747* **Comparative latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort.
48* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price. See Pricing for cache writes, long-context, and per-platform pricing.
48* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for cache writes, long-context, and per-platform pricing.
4949* **Claude API ID:** Every Claude model ID is a pinned snapshot, including the dateless IDs used from the 4.6 generation on.
5050* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual thinking.type “enabled” + budget\_tokens mode on earlier models; it is deprecated on Claude Opus 4.6 and Claude Sonnet 4.6 and not accepted on later models.
5151* **Default effort:** The effort parameter’s default on the Claude API. Set effort explicitly to use a different level.
models/sonnet-4-5/overview Changed · +1 / -1 lines
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/sonnet-4-6/overview Changed · +1 / -1 lines
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/sonnet-5/overview Changed · +1 / -1 lines
from line 31
3131
3232* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3333* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
34* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price. See Pricing for the full list.
34* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1). See Pricing for the full list.
3535* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3636* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3737* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.