overview changedrelease-notes/overview
Recorded here
Lines+8added
Lines−6removed
From line
14
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits79to this page, all time
The whole hunk
from line 14, old and new numbered
/
from line 14
1414
1515### November 9, 2026
1616
17* We’ve launched **Claude Fable 5.2** (`claude-fable-5-2`), built for demanding reasoning and long-horizon agentic work. **Claude Mythos 5.2** (`claude-mythos-5-2`) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Both models have a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). They cost $8 USD per MTok of input and $40 USD per MTok of output (Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per MTok of input and $50 USD per MTok of output). Claude Fable 5.2 is available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). It’s also available on [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). It’s also available on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). It’s also available on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2) for API changes and migration guidance. For model-specific prompting patterns, see [Prompting Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2).
17* We’ve launched **Claude Fable 5.2** (`claude-fable-5-2`), built for demanding reasoning and long-horizon agentic work. **Claude Mythos 5.2** (`claude-mythos-5-2`) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Both models have a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). They cost $8 USD per MTok of input and $40 USD per MTok of output (Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per MTok of input and $50 USD per MTok of output). Claude Fable 5.2 is available on the Claude API, [Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2) for API changes and migration guidance. For model-specific prompting patterns, see [Prompting Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2).
1818* Claude Fable 5.2 and Claude Mythos 5.2 enforce the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) for every account, whatever its age. Claude Fable 5.1 returns the error by default on accounts created on or after August 31, 2026 (see [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement)). If your code edits the `system` prompt, `tools`, or an earlier message and then sends back a Claude Fable 5.2 or Claude Mythos 5.2 thinking block from a later turn, the request returns a 400 error. Before you switch, [check whether your code edits the prefix](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-preserved-thinking).
19* On the Claude API and Claude Models on Google Cloud (Google managed), a conversation that moves onto Claude Fable 5.2 or Claude Mythos 5.2 keeps the reasoning from other models, including Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. When the conversation moves the other way, to any other model, including Claude Opus 5.5 and Claude Fable 5.1, the API drops the thinking blocks that Claude Fable 5.2 or Claude Mythos 5.2 produced, and the request still succeeds. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
19* Claude Fable 5.2 and Claude Mythos 5.2 read other models’ thinking blocks on the Claude API and Claude Models on Google Cloud (Google managed). So on those platforms, a conversation that moves onto either model keeps its reasoning. The other models include Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5.
20* No other model reads thinking blocks from Claude Fable 5.2 or Claude Mythos 5.2. When a conversation moves from either one to a model outside this pair, the API drops those blocks. That includes a move to Claude Opus 5.5 or Claude Fable 5.1. The request still succeeds. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
2021* Claude Fable 5.2 and Claude Mythos 5.2 support computer use through the `computer_toolset_20260801` toolset. A request that declares the earlier `computer_20251124` tool returns a 400 error on every platform except Amazon Bedrock, where the earlier tool still works. See [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).
2122* With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), which is in beta, a Claude Fable 5.2 or Claude Mythos 5.2 executor accepts only Claude Fable 5.2 or Claude Mythos 5.2 as its advisor. Any other advisor returns a 400 error, so set the advisor’s `model` to one of these two models when you move an executor to them. Every executor model accepts Claude Fable 5.2 as its advisor. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
2223* Both models require 30-day data retention, like Claude Fable 5.1 and Claude Mythos 5.1. They aren’t available under zero data retention unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
2324* Thinking blocks that Claude Fable 5.2 and Claude Mythos 5.2 produce work only in the account that produced them, or in an account linked to it. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
25* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5.2. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability).
2426* We’ve launched [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Fable 5.2 in Messages API requests on the Claude API. Fast mode delivers up to 2.5x higher output tokens per second, at $16 USD per MTok of input and $80 USD per MTok of output. Set `speed: "fast"` on your request, with no beta header.
2527
2628### November 5, 2026
from line 176
174176
175177### September 1, 2026
176178
177* We’ve launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.
179* We’ve launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research. For Project Glasswing participants, we’ve also launched **Claude Mythos 5.1** (`claude-mythos-5-1`). Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). They cost $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). It’s also on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for specifications.
178180* Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the base input price, compared with 0.1x on other models. Cache writes are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).
179181* On Claude Fable 5.1 and Claude Mythos 5.1, `tool_choice` types `any` and `tool` aren’t supported and return a 400 error. `auto` and `none` are unchanged. To guarantee schema-conformant tool inputs, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs).
180182* Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can’t read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also [checks that nothing before a block has changed](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): for new accounts created on or after August 31, 2026, replaying one after the `system` prompt, `tools`, or an earlier message changed returns a 400 error. With the `thinking-binding-controls-2026-08-01` beta header, dropped blocks are reported in an `input_transformations` response field, and `thinking.block_binding.prefix_mismatch_behavior` chooses between rejecting and dropping blocks whose history changed. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking).
from line 250
248250
249251### July 24, 2026
250252
251* We’ve launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It’s available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.
252* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview).
253* We’ve launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It’s available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.
254* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [Effort with thinking](https://platform.claude.com/docs/en/build-with-claude/effort#effort-with-thinking).
253255* [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) is the primary control for steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work.
254256* Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the `mid-conversation-tool-changes-2026-07-01` beta header in your requests.
255257* The `fallbacks` parameter now supports a `"default"` mode, which applies Anthropic’s recommended fallback models by refusal category. Server-side fallback is in beta, and the `"default"` mode requires the `server-side-fallback-2026-07-01` beta header. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
from line 298
296298
297299### June 30, 2026
298300
299* We’ve launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [What’s new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details and migration guidance. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).
301* We’ve launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).
300302* Claude Managed Agents session event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). Opt in with the `event_deltas[]` query parameter on `GET /v1/sessions/{session_id}/events/stream`. The `event_start` and `event_delta` events preview an agent message’s text as it’s generated, before the complete `agent.message` event arrives.
301303* [Listing sessions](https://platform.claude.com/docs/en/managed-agents/session-operations#listing-sessions) for Claude Managed Agents now supports backward pagination. `GET /v1/sessions` returns a `prev_page` cursor alongside `next_page`; pass it as the `page` parameter to return to the previous page. See [Pagination](https://platform.claude.com/docs/en/api/overview#pagination).
302304* When creating a Claude Managed Agents session, you can now [override the agent’s configuration for that session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session). Pass `agent` with `type: "agent_with_overrides"` to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged.
No line in this hunk matches that.