2026-09-26 08:28 UTC · anthropic/api-release-notes · live page
Summary by gemma-4-12b. It may be wrong; the diff below is what actually changed. Raw: 338f19e464-anthropic-api-release-notes.diff · commit 338f19e464
diff --git a/snapshots/anthropic/api-release-notes.md b/snapshots/anthropic/api-release-notes.mdindex 8fbc515..f52c9d5 100644--- a/snapshots/anthropic/api-release-notes.md+++ b/snapshots/anthropic/api-release-notes.md@@ -9,6 +9,24 @@ For release notes on Claude Apps, see the Release notes for Claude Apps in the C For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` repository. +### September 24, 2026++- We're resuming billing for refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. Refusals billed under this change are charged like any other request, at the rates of the model that ran it. Refusals before any output in other categories are still not billed, and fallback credit is unchanged. This change applies on all platforms. See How refusals are billed.+- The Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`). See Sessions on users' machines.+- The Compliance API Activity Feed no longer returns file names, project document names, or artifact titles. The `filename` and `title` fields on file, project document, and artifact activities are now always empty or omitted, including on activities recorded before this change. To look up a name or title by the ID on the activity, use a Compliance Access Key with the `read:compliance_user_data` scope. See Understand the Activity object.++### September 23, 2026++- Cache diagnostics is out of beta on the Claude API and no longer requires the `cache-diagnosis-2026-04-07` beta header. Include the `diagnostics` object on a Messages request to opt in; requests that still send the header work as before. Responses from `POST /v1/messages` now always include the `diagnostics` field, which is `null` when the request did not include the `diagnostics` object.++### September 22, 2026++- We've launched Claude Opus 5.5 (`claude-opus-5-5`), a model for long-running agentic coding and knowledge work. It has a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking, at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25). Claude Opus 5.5 is available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud, and Claude in Microsoft Foundry. See What's new in Claude Opus 5.5 for capabilities, API changes, and migration guidance.+- On Claude Opus 5.5, thinking can't be disabled: `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}` return a 400 error. Omit the `thinking` field and control thinking depth with the effort parameter. `tool_choice` types `any` and `tool` also return a 400 error, as on Claude Fable 5.1; use `auto` with strict tool use. On the Claude API and Google Cloud, computer use on this model requires the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool returns a 400 error; on Amazon Bedrock, `computer_20251124` keeps working. See the migration guide.+- Fast mode (research preview) is available for Claude Opus 5.5 on the Claude API.+- Tools can now be defined inside a mid-conversation system message, in beta on the Claude API with the `inline-tools-2026-09-15` beta header. A `tool_addition` block can carry the tool's full definition (`tool: {"type": "tool_definition", "definition": {...}}`), so you can add a tool, change its schema, or move a server tool to a newer version without editing `tools` or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's `mcp-client-2026-09-15` beta header as well, the definition can be an MCP toolset, and a response records each server's fetched tool list in an `mcp_tool_listing` block, which pins that list when you send it back.+ ### September 18, 2026 +- For cache diagnostics, a response to a request that sends the `cache-diagnosis-2026-04-07` beta header now always includes the `diagnostics` field. The field is `null` when the request did not include the `diagnostics` object. Previously the field was omitted in that case. - The Compliance API local session endpoints now also return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See Sessions on users' machines. @@ -16,4 +34,5 @@ For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` r - The Messages API can now compact a conversation on demand on the Claude API, in beta with the `compact-2026-09-04` beta header. Send the top-level `compaction` parameter, and the API returns a signed `compaction` block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid.+- With the `thinking-binding-controls-2026-08-01` beta header, the `input_transformations` response field gains a second entry type, `thinking_mismatch_allowed`. It names a thinking block that failed the prefix check on a request where the API doesn't enforce that check: on Claude Fable 5.1, for example, a request from an account created before August 31, 2026, with `prefix_mismatch_behavior` unset. The block still reaches the model unchanged. Log these entries to find history edits in production traffic before you opt into enforcement. See Set the mismatch behavior and read `input_transformations`. ### September 10, 2026@@ -22,4 +41,8 @@ For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` r - Version 1.32.0 of the `ant` CLI adds `ant beta:sessions connect`, which attaches your terminal to a Claude Managed Agents session. You can follow the session live, send messages, and allow or deny tool calls that are waiting for approval. Pass `--web` to serve the Claude Console's session viewer locally and open the session there instead. See Connect to a Managed Agents session from your terminal. +### September 9, 2026++- For cache diagnostics, the API now stores a request's fingerprint only when the request includes the `diagnostics` object. A request that sends only the `cache-diagnosis-2026-04-07` beta header is still accepted, but no fingerprint is stored. A later turn that points `previous_message_id` at it reports `previous_message_not_found`. Include `diagnostics` on every turn, with `"previous_message_id": null` on the first.+ ### September 3, 2026 @@ -195,5 +218,5 @@ For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` r ### June 9, 2026 -- We've launched Claude Fable 5 (`claude-fable-5`), our most capable widely released model, alongside Claude Mythos 5 (`claude-mythos-5`) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability.+- We've launched Claude Fable 5 (`claude-fable-5`), our most capable model open to all customers, alongside Claude Mythos 5 (`claude-mythos-5`) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability. - Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7. Compared to models before Claude Opus 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the token counting API with `model: "claude-fable-5"` to measure your prompts under the new tokenizer. - Claude Fable 5 runs safety classifiers on requests and during response generation. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"`. You are not billed for a request refused before any output is generated. An opt-in `fallbacks` parameter (in beta on the Claude API and Claude Platform on AWS; not supported on the Message Batches API) re-runs refused requests on another model, billed at the fallback model's rates. See Handling stop reasons.@@ -223,5 +246,5 @@ For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` r ### May 28, 2026 -- We've launched Claude Opus 4.8 (), our most capable widely released model. Claude Opus 4.8 supports a 1M token context window by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7. See the migration guide for baseline settings, features, and migration guidance.+- We've launched Claude Opus 4.8 (), our most capable model. Claude Opus 4.8 supports a 1M token context window by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7. See the migration guide for baseline settings, features, and migration guidance. - We've launched mid-conversation system messages. On Claude Opus 4.8, you can send `role: "system"` messages after a user turn (subject to placement rules) in the `messages` array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required. - The `stop_details` field on refusal responses is now publicly documented; it returns a `category` (`cyber`, `bio`, or `null`) and a human-readable `explanation`, so your application can route different classes of refusal to the right next step. No beta header is required.@@ -302,5 +325,5 @@ For updates to Claude Code, see the complete CHANGELOG.md in the `claude-code` r ### April 16, 2026 -- We've launched Claude Opus 4.7, our most capable widely released model for complex reasoning and agentic coding, at the same $5 / $25 per MTok pricing as Opus 4.6. See What's new in Claude Opus 4.7 for capability improvements, new features, and the updated tokenizer. Opus 4.7 includes API breaking changes versus Opus 4.6; see the migration guide before upgrading.+- We've launched Claude Opus 4.7, our most capable model for complex reasoning and agentic coding, at the same $5 / $25 per MTok pricing as Opus 4.6. See What's new in Claude Opus 4.7 for capability improvements, new features, and the updated tokenizer. Opus 4.7 includes API breaking changes versus Opus 4.6; see the migration guide before upgrading. - Claude in Amazon Bedrock is now open to all Amazon Bedrock customers. Claude Opus 4.7 and Claude Haiku 4.5 are available self-serve from the Bedrock console through the Messages API endpoint at `/anthropic/v1/messages`, in 27 AWS regions with global and regional endpoints. - We've launched task budgets in beta on Claude Opus 4.7. Give Claude an advisory token budget for a full agentic loop (thinking, tool calls, tool results, and output) and the model sees a running countdown, using it to prioritize work and finish gracefully as the budget is consumed. Include the `task-budgets-2026-03-13` beta header in your requests.