---
name: Claude Platform
slug: claude-platform
type: scrape
source_url: https://platform.claude.com/docs/en/release-notes/overview
organization: Anthropic
organization_slug: anthropic
total_releases: 17
latest_version: Opus 4.7
latest_date: 2026-04-16
last_updated: 2026-04-16
tracking_since: 2026-01-05
canonical: https://releases.sh/anthropic/claude-platform
organization_url: https://releases.sh/anthropic
---

<Summary type="rolling" window-days="90" release-count="15">
Claude Platform shipped a major model refresh and expanded its agentic capabilities. Opus 4.7 arrived with improved reasoning and broke API compatibility, requiring migration from earlier versions; Sonnet 4.6 landed as a faster balanced option with extended thinking and 1M context now generally available at standard pricing. The platform grew its agent-building toolkit with Managed Agents (fully sandboxed autonomous operation), an advisor tool (pairing fast executors with high-intelligence guidance), and the `ant` CLI for streamlined local development. Automatic caching simplified request optimization, the compaction API enabled effectively infinite conversations through server-side summarization, and capability discovery moved into the Models API itself.
</Summary>

<Summary type="monthly" period="March 2026" release-count="4">
Extended output and expanded context reached general availability this month. The 1M token context window graduated to standard pricing for Claude Opus 4.6 and Sonnet 4.6, with the media limit per request raised to 600 images or PDFs. The max_tokens cap on Batches API grew to 300k for longer single-turn outputs, while a new display field for extended thinking lets developers omit thinking blocks for faster streaming. The Models API gained capability fields exposing max_input_tokens, max_tokens, and a capabilities object for runtime model discovery. The 1M context beta for Sonnet 4.5 and 4 retires April 30, after which requests exceeding 200k tokens will error on those models.
</Summary>

<Release version="Opus 4.7" date="April 16, 2026" published="2026-04-16T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#opus-4-7">
## Claude Opus 4.7 released

Launched Claude Opus 4.7, the most capable generally available model for complex reasoning and agentic coding, at the same $5 / $25 per MTok pricing as Opus 4.6. Opus 4.7 includes API breaking changes versus Opus 4.6; see migration guide before upgrading. Includes capability improvements, new features, and updated tokenizer.
</Release>

<Release date="April 14, 2026" published="2026-04-14T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-sonnet-4-and-claude-opus-4-deprecation-announced">
## Claude Sonnet 4 and Claude Opus 4 deprecation announced

We announced the deprecation of the Claude Sonnet 4 model (`claude-sonnet-4-20250514`) and the Claude Opus 4 model (`claude-opus-4-20250514`), with retirement on the Claude API scheduled for June 15, 2026. We recommend migrating to Claude Sonnet 4.6 and Claude Opus 4.6 respectively.
</Release>

<Release date="April 9, 2026" published="2026-04-09T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#advisor-tool-launched-in-public-beta">
## Advisor tool launched in public beta

Launched the [advisor tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/advisor-tool) in public beta. Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation. Long-horizon agentic workloads get close to advisor-solo quality while the bulk of token generation happens at executor-model rates. Include the beta header `advisor-tool-2026-03-01` in your requests.
</Release>

<Release date="April 8, 2026" published="2026-04-08T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-managed-agents-and-ant-cli-launched">
## Claude Managed Agents and ant CLI launched

Launched **Claude Managed Agents** in public beta, a fully managed agent harness for running Claude as an autonomous agent with secure sandboxing, built-in tools, and server-sent event streaming. Create agents, configure containers, and run sessions through the API. All endpoints require the `managed-agents-2026-04-01` beta header.

Launched the **`ant` CLI**, a command-line client for the Claude API that enables faster interaction with the Claude API, native integration with Claude Code, and versioning of API resources in YAML files.
</Release>

<Release date="April 7, 2026" published="2026-04-07T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-mythos-preview-and-claude-in-amazon-bedrock-available">
## Claude Mythos Preview and Claude in Amazon Bedrock available

Announced [Claude Mythos Preview](https://anthropic.com/glasswing) available as a gated research preview for defensive cybersecurity work as part of [Project Glasswing](https://anthropic.com/glasswing). Access is invitation-only.

The [Messages API](https://platform.claude.com/docs/en/release-notes/overview/docs/en/api/messages) is now available on Amazon Bedrock as a research preview. The new Claude in Amazon Bedrock endpoint at `/anthropic/v1/messages` uses the same request shape as the first-party Claude API and runs on AWS-managed infrastructure. Available in `us-east-1`; contact your Anthropic account executive to request access.
</Release>

<Release date="March 30, 2026" published="2026-03-30T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#max-tokens-cap-raised-to-300k-and-1m-context-window-beta-ret">
## Max tokens cap raised to 300k and 1M context window beta retirement scheduled

Raised the `max_tokens` cap to 300k on the [Message Batches API](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/batch-processing#extended-output-beta) for Claude Opus 4.6 and Sonnet 4.6. Include the `output-300k-2026-03-24` beta header to generate longer single-turn outputs.

Retiring the 1M token context window beta for Claude Sonnet 4.5 and Claude Sonnet 4 on **April 30, 2026**. After that date, the `context-1m-2025-08-07` beta header will have no effect on these models, and requests that exceed the standard 200k-token context window will return an error. Migrate to Claude Sonnet 4.6 or Claude Opus 4.6, which support the full 1M token context window at standard pricing with no beta header required.
</Release>

<Release date="March 18, 2026" published="2026-03-18T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview">
## Model capability fields added to Models API

Added model capability fields to the Models API. `GET /v1/models` and `GET /v1/models/{model_id}` now return `max_input_tokens`, `max_tokens`, and a `capabilities` object. Query the API to discover what each model supports.
</Release>

<Release date="March 16, 2026" published="2026-03-16T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#extended-thinking-display-field-launched">
## Extended thinking display field launched

Launched the `display` field for extended thinking, letting you omit thinking content from responses for faster streaming. Set `thinking.display: "omitted"` to receive thinking blocks with an empty `thinking` field and the `signature` preserved for multi-turn continuity. Billing is unchanged.
</Release>

<Release date="March 13, 2026" published="2026-03-13T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#1m-token-context-window-now-generally-available-and-media-li">
## 1M token context window now generally available and media limit increased

The [1M token context window](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/context-windows) is now generally available for Claude Opus 4.6 and Sonnet 4.6 at standard pricing. Requests over 200k tokens work automatically for these models with no beta header required. The 1M token context window remains in beta for Claude Sonnet 4.5 and Sonnet 4.

Removed the dedicated 1M rate limits for all supported models. Your standard account limits now apply across every context length.

Raised the media limit from 100 to 600 images or PDF pages per request when using the 1M token context window.
</Release>

<Release date="February 19, 2026" published="2026-02-19T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#automatic-caching-for-messages-api-and-model-retirements">
## Automatic caching for Messages API and model retirements

Launched **automatic caching** for the Messages API. Add a single `cache_control` field to your request body and the system automatically caches the last cacheable block, moving the cache point forward as conversations grow. No manual breakpoint management required. Works alongside existing block-level cache control for fine-grained optimization. Available on the Claude API and Azure AI Foundry (preview).

Retired the Claude Sonnet 3.7 model (`claude-3-7-sonnet-20250219`) and the Claude Haiku 3.5 model (`claude-3-5-haiku-20241022`). All requests to these models will now return an error. Announced the deprecation of the Claude Haiku 3 model (`claude-3-haiku-20240307`), with retirement scheduled for April 19, 2026.
</Release>

<Release date="February 17, 2026" published="2026-02-17T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-sonnet-4-6-released-with-extended-thinking-and-1m-con">
## Claude Sonnet 4.6 released with extended thinking and 1M context window

Launched [Claude Sonnet 4.6](https://www.anthropic.com/news/claude-sonnet-4-6), our latest balanced model combining speed and intelligence. Sonnet 4.6 delivers improved agentic search performance while consuming fewer tokens. Supports [extended thinking](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/extended-thinking) and a [1M token context window](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/context-windows) (beta).

API [code execution](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/code-execution-tool) is now **free when used with web search or web fetch**.

The [web search tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/web-search-tool) and [programmatic tool calling](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) are now generally available (no beta header required). Web search and web fetch now support [dynamic filtering](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/web-search-tool#dynamic-filtering).

The [code execution tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/code-execution-tool), [web fetch tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/web-fetch-tool), [tool search tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/tool-search-tool), [tool use examples](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/define-tools#providing-tool-use-examples), and [memory tool](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/memory-tool) are now generally available (no beta header required).
</Release>

<Release date="February 7, 2026" published="2026-02-07T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#fast-mode-in-research-preview-for-opus-4-6">
## Fast mode in research preview for Opus 4.6

Launched [fast mode](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/fast-mode) in research preview for Opus 4.6, providing significantly faster output token generation via the `speed` parameter. Fast mode is up to 2.5x as fast at premium pricing. Interested customers can join the [waitlist](https://claude.com/fast-mode).
</Release>

<Release date="February 5, 2026" published="2026-02-05T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-opus-4-6-released-with-adaptive-thinking-and-compacti">
## Claude Opus 4.6 released with adaptive thinking and compaction API

We've launched Claude Opus 4.6, our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends adaptive thinking (`thinking: {type: "adaptive"}`); manual thinking (`type: "enabled"` with `budget_tokens`) is deprecated. The effort parameter is now generally available and supports Claude Opus 4.6. We've launched the compaction API in beta, providing server-side context summarization for effectively infinite conversations. Introduced data residency controls with the `inference_geo` parameter for US-only inference at 1.1x pricing. The 1M token context window is now available in beta for Claude Opus 4.6. Fine-grained tool streaming is now generally available on all models.
</Release>

<Release date="February 5, 2026" published="2026-02-05T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-opus-4-6-released-with-adaptive-thinking-and-new-feat">
## Claude Opus 4.6 released with adaptive thinking and new features

Launched [Claude Opus 4.6](https://www.anthropic.com/news/claude-opus-4-6), our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends [adaptive thinking](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/adaptive-thinking) (`thinking: {type: "adaptive"}`); manual thinking (`type: "enabled"` with `budget_tokens`) is deprecated. Opus 4.6 does not support prefilling assistant messages.

The [effort parameter](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/effort) is now generally available (no beta header required) and supports Claude Opus 4.6.

Launched the [compaction API](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/compaction) in beta, providing server-side context summarization for effectively infinite conversations.

Introduced [data residency controls](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/data-residency), allowing you to specify where model inference runs with the `inference_geo` parameter. US-only inference available at 1.1x pricing.

The [1M token context window](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/context-windows) is now available in beta for Claude Opus 4.6. [Long context pricing](https://platform.claude.com/docs/en/release-notes/overview/docs/en/about-claude/pricing#long-context-pricing) applies to requests exceeding 200k input tokens.

[Fine-grained tool streaming](https://platform.claude.com/docs/en/release-notes/overview/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) is now generally available on all models and platforms (no beta header required). The `output_format` parameter for [structured outputs](https://platform.claude.com/docs/en/release-notes/overview/docs/en/build-with-claude/structured-outputs) has been moved to `output_config.format`.
</Release>

<Release date="January 29, 2026" published="2026-01-29T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#structured-outputs-now-generally-available">
## Structured outputs now generally available

Structured outputs are now generally available on the Claude API for Claude Sonnet 4.5, Claude Opus 4.5, and Claude Haiku 4.5. GA includes expanded schema support, improved grammar compilation latency, and simplified integration with no beta header required. The `output_format` parameter has moved to `output_config.format`.
</Release>

<Release date="January 12, 2026" published="2026-01-12T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#console-redirects-to-platform-claude-com">
## Console redirects to platform.claude.com

`console.anthropic.com` now redirects to `platform.claude.com`. The Claude Console has moved to its new home as part of Claude brand consolidation. Existing bookmarks and links will continue working via automatic redirect.
</Release>

<Release date="January 5, 2026" published="2026-01-05T00:00:00.000Z" url="https://platform.claude.com/docs/en/release-notes/overview#claude-opus-3-model-retired">
## Claude Opus 3 model retired

We've retired the Claude Opus 3 model (`claude-3-opus-20240229`). All requests to this model will now return an error. We recommend upgrading to Claude Opus 4.5, which offers significantly improved intelligence at a third of the cost.
</Release>