The Senior Colleague Who Tells You When It Is Not Sure
Claude has moved beyond careful chat. On September 1, 2026 Anthropic released Claude Fable 5.1 and Claude Mythos 5.1, and that is the largest change in this guide for months: 1M token context by default, 128k maximum output, always-on adaptive thinking, the same $10 / $50 headline price as Fable 5, and cache reads four times cheaper. Opus 5 sits below that ceiling at half the price; Sonnet 5 holds the Free and Pro default, and the price rise this guide reported as canceled did not arrive on September 1. Code, Cowork, Tag, Design and Microsoft 365 integrations put Claude inside the places work happens. Two items belong in the procurement file ahead of everything else: Fable 5.1 and Mythos 5.1 both require 30-day data retention and are not available under zero data retention unless Anthropic authorizes it, and 5.1 carries three breaking changes that will fail a working integration rather than warn it.
The colleague who will not pretend the work is done
Claude’s most useful personality trait is judgment. It is unusually willing to identify missing evidence, challenge the brief and keep uncertainty visible while still moving the task forward.
Careful without being passive
Claude reads deeply, preserves nuance and usually prefers an explicit caveat to a neat but unsupported conclusion.
- Strong source fidelity
- Structured, professional writing
- Useful self-review and error detection
Work where judgment matters
Long documents, complex coding, regulated analysis, technical reviews and deliverables that need a defensible reasoning trail.
- Board and client materials
- Repository-scale engineering
- Financial, legal and scientific workflows
The brief may itself be wrong
Claude is especially valuable when the input is incomplete, internally inconsistent or likely to push a model toward a polished fiction.
- Ask it to inspect the premise
- Invite direct disagreement
- Require uncertainty to remain visible
Analyze this proposal for the executive team. Before recommending anything, identify what is missing, internally inconsistent or too weakly evidenced to support a decision.
Create the strongest defensible synthesis from these sources. Separate: verified facts, reasonable inferences, unresolved questions and claims the material cannot support.
Fable 5.1 and Mythos 5.1 arrive, and the cache line is the real news
Anthropic released Claude Fable 5.1 and Claude Mythos 5.1 on September 1, 2026: model ids claude-fable-5-1 and claude-mythos-5-1, 1M token context by default, 128k maximum output and always-on adaptive thinking. Anthropic’s own framing is blunt: “They’re the world’s most advanced models for coding and knowledge work.” Treat that as a vendor claim. The headline price is unchanged from Fable 5 at $10 / $50 per million tokens, so the interesting number is further along the row: a cache hit on 5.1 costs $0.25 per million tokens against $1 on Fable 5, which is 0.025x base input where every other Claude model charges 0.1x. Three breaking changes ride along with the release, and both 5.1 models require 30-day data retention. Two September 1 non-events matter as much: the Sonnet 5 price rise this guide called canceled did not occur, and no Claude model retired.
| Model | Base input | 5m cache write | 1h cache write | Cache hit | Output |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10 | $12.50 | $20 | $0.25 | $50 |
| Claude Mythos 5.1, limited availability | $10 | $12.50 | $20 | $0.25 | $50 |
| Claude Fable 5 | $10 | $12.50 | $20 | $1 | $50 |
| Claude Mythos 5, limited availability | $10 | $12.50 | $20 | $1 | $50 |
| Claude Opus 5 | $5 | $6.25 | $10 | $0.50 | $25 |
| Claude Sonnet 5 | $2 | $2.50 | $4 | $0.20 | $10 |
| Claude Haiku 4.5 | $1 | $1.25 | $2 | $0.10 | $5 |
| Model | Where it sits | Status on September 3, 2026 |
|---|---|---|
| Claude Fable 5.1 | Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud and Microsoft Foundry | Released September 1, 2026; the only Fable model now listed on the models overview |
| Claude Mythos 5.1 | Not generally available | Limited availability. Anthropic: available to vetted cyberdefenders and life scientists |
| Claude Fable 5 | Still selectable and still priced | Active and still on the pricing page, but no longer listed on the models overview |
| Claude Opus 5 | Claude Max default and strongest model on Claude Pro, per the July 24 announcement | Released July 24, 2026; the per-plan defaults remain unconfirmed since August 19 |
| Claude Sonnet 5 | Claude Free and Claude Pro | $2 / $10 confirmed as the standard price; the September 1 rise did not occur |
| Claude Haiku 4.5 | Not a plan default; the cheapest priced tier | Active, but claude-haiku-4-5-20251001 carries a tentative retirement floor of “Not sooner than October 15, 2026” |
| Claude Opus 4.1 | Nowhere; the identifier stops serving requests | Retired August 5, 2026; the replacement was claude-opus-4-8 |
Claude Fable 5.1 New, September 1
The new top of the generally available lineup, at model id claude-fable-5-1. Anthropic positions Fable 5.1 and Mythos 5.1 together as “the world’s most advanced models for coding and knowledge work,” which is a vendor claim and should be treated as one until your own evaluation says otherwise. The specification changes that matter operationally are the defaults: 1M token context is the default rather than a beta flag, maximum output is 128k, and adaptive thinking is always on, so there is no configuration in which this model is not reasoning before it answers.
- 1M token context by default; 128k maximum output
- Always-on adaptive thinking, not a toggle
- Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, Microsoft Foundry
- $10 / $50 per million tokens, with cache hits at $0.25
- Requires 30-day data retention; no zero data retention unless Anthropic authorizes it
Claude Mythos 5.1 Limited availability
The gated tier, at model id claude-mythos-5-1, sharing Fable 5.1’s specification and price. Access has been reframed since the last edition. The September 1 announcement describes it through two named programs, the Cyber Verification Program and the Life Sciences Verification Program: “Claude Mythos 5.1 is available to vetted cyberdefenders and life scientists.” Anthropic’s release notes still describe claude-mythos-5-1 as being for Project Glasswing participants. The two first-party sources frame the same gate differently, and this guide reports both rather than choosing the tidier one. Either way it is not generally available, so do not build a plan on it.
- Lead with the verification programs: Cyber Verification and Life Sciences Verification
- Release notes still say Project Glasswing participants; the two framings differ
- Same 1M context, 128k output and $10 / $50 pricing as Fable 5.1
- Requires 30-day data retention, like Fable 5.1
- Not generally available, so it is not a procurement option today
Breaking change: tool_choice 5.1 returns 400
On Fable 5.1 and Mythos 5.1, the tool_choice types any and tool are not supported and return a 400. The types auto and none are unchanged. Anthropic’s stated alternatives are strict tool use or structured outputs. This is the breaking change most likely to be sitting in production code right now, because forcing a tool call has been a standard way to guarantee a parseable response. Search your codebase for the two removed values before you route any traffic to a 5.1 model.
anyandtoolreturn 400 on 5.1autoandnonebehave as before- Use strict tool use or structured outputs instead
- This fails the request; it does not degrade quietly
Breaking change: thinking blocks 5.1 returns 400
Thinking blocks are preserved only for the model that produced them or a newer one. For accounts created on or after August 31, 2026, replaying a thinking block after a changed system prompt, changed tools or a changed message returns a 400. The beta header thinking-binding-controls-2026-08-01 controls this behavior. The practical exposure is any pattern that caches an assistant turn and replays it against an edited prompt, which is common in agent frameworks and in evaluation harnesses that mutate the system prompt between runs. Note the account-age condition: an older account may not see the error, so a team can be split between working and failing on identical code.
- Thinking blocks survive only into the producing model or newer
- Accounts created on or after August 31, 2026 get a 400 on a changed system prompt, tools or message
- Controlled by the beta header
thinking-binding-controls-2026-08-01 - Older and newer accounts can behave differently on the same code
Claude Opus 5 The no-retention tier
Released July 24, 2026 at $5 / $25 per million tokens with a $0.50 cache hit, 1M context and 128k maximum output. Its role has quietly sharpened with the 5.1 release: Opus 5 is now the most capable Claude model that does not carry a mandatory retention requirement, which makes it the natural home for regulated traffic that cannot sit under a 30-day window. Anthropic places it within 0.5% of Fable 5’s peak score on the benchmark it cites and describes fast mode as 2.5x faster at 2x base price. Both are vendor claims; time them on your own traffic. The July 24 announcement made Opus 5 the Claude Max default and the strongest model on Claude Pro, and that per-plan claim has been unconfirmed since August 19, 2026 because anthropic.com/pricing returned a 403 and no other readable page restates it.
- $5 / $25 per million tokens; cache hit $0.50
- No data-retention requirement, unlike Fable 5.1 and Mythos 5.1
- Per-plan defaults date to July 24 and remain unconfirmed
- In Claude Code, Claude Cowork and on Microsoft Foundry
Claude Fable 5 Active, off the overview
Fable 5 has not been retired and has not been repriced: $10 / $50 per million tokens with a $1 cache hit, and it is still on the pricing page. What changed on September 1 is visibility. The models overview page now lists only Fable 5.1, so a reader who checks the overview will not find Fable 5 there and may conclude it is gone. It is not. Treat the overview as the recommendation and the pricing page as the inventory. Fable 5 also carries the same 30-day retention requirement as the 5.1 pair.
- Still active and still priced at $10 / $50
- Absent from the models overview; present on the pricing page
- Cache hits cost $1, four times the 5.1 rate
- Also a retention-required model
Claude Sonnet 5 Free and Pro default
Anthropic’s most agentic Sonnet, at $2 / $10 per million tokens with a $0.20 cache hit. The pricing question that hung over it is now settled by the calendar rather than by a promise: the scheduled September 1 increase did not occur, and $2 / $10 is the standard price. It plans, uses browsers and terminals, and approaches Opus 4.8 performance on some tasks at a lower operating cost, per Anthropic.
- $2 / $10 is the standard price, confirmed after September 1 passed
- Default for Free and Pro per the July 24 announcement; that per-plan default is still unconfirmed
- Budget renewals and volume forecasts can rest on it
Claude Opus 4.8 Status unconfirmed
Two softenings this guide made in August still stand. Opus 4.8 is not described as a safety fallback anywhere readable. And its legacy label could not be re-verified: the models overview has a “Legacy models” heading whose body is rendered in JavaScript and returned empty. Opus 4.8 is absent from the latest-models comparison table and appears only in incidental notes, which is suggestive rather than quotable.
- Legacy label unconfirmed; treat the July reading as the last confirmed one
- Anthropic’s figure: four times less likely than Opus 4.7 to let flaws in its own code pass, a vendor claim
- Microsoft’s July 24, 2026 announcement says Opus 5 replaces it in the Microsoft 365 Copilot lineup
Where a blocked request goes Softened
This guide previously said Fable falls back specifically to Opus 5. Re-checked on September 3, 2026, that precision is not supported by anything first-party. Anthropic’s readable wording is plural and unnamed: “Our safeguards do, however, still redirect several kinds of dual-use cybersecurity tasks...to our Opus models. This includes penetration testing, exploit generation, and binary-based vulnerability scanning.” No first-party page names Opus 5 as the destination. Say “an Opus model” in your runbooks and user-facing notes, not a version number, because the version number is this guide’s inference and not Anthropic’s statement. On the API, the fallbacks parameter accepts a "default" mode applying Anthropic’s recommended fallback per refusal category; server-side fallback is in beta.
- The destination is “our Opus models,” plural and unnamed
- Named dual-use categories: penetration testing, exploit generation, binary-based vulnerability scanning
- Repoint any runbook that names a specific fallback model
- Anthropic’s August 7 figures, roughly 85% fewer false positives and under 5% of Fable 5 sessions triggering a fallback, remain vendor figures
Workbench is Playground, with dates Aug 17 and Aug 18
The rename is now dated on both ends. The legacy Workbench at platform.claude.com/workbench sunset on August 17, 2026, and the August 18, 2026 release note names the replacement at platform.claude.com/playground. Playground supports every Messages API parameter and shows the full SDK request beside the API response, so it is a capability gain rather than a like-for-like port. It is also a rename your onboarding material, internal wiki links and screenshots will not have caught.
- Old URL sunset August 17, 2026
- New URL documented in the August 18, 2026 release note
- Sweep internal links and training material
Python SDK v1.0 is a breaking release August 20
Anthropic shipped Python SDK v1.0 on August 20, 2026 with four changes that will stop a build rather than warn it: the HTTP layer moved from httpx to httpx2, Python 3.10 or later is now required, Text Completions was removed outright, and temperature, top_p and top_k were removed from Messages. Pin your SDK version and read the migration before an unattended upgrade does it for you.
- httpx to httpx2
- Python 3.10 or later required
- Text Completions removed
temperature,top_pandtop_kremoved from Messages
Compliance and Admin API mature August 26
On August 26, 2026 the Compliance API session endpoints left beta for Claude Cowork and Claude Code, and the Admin API became available in the ant CLI and across all SDKs. The first of those is the one to tell your records team about: transcript retrieval for agent sessions is no longer a beta surface you were told not to build a retention process on.
- Compliance API session endpoints out of beta for Cowork and Claude Code
- Admin API in the
antCLI and all SDKs - Re-test coverage before it carries a legal retention obligation
Console keys, Files and Skills August 27
On August 27, 2026 the Console gained personal keys and service account keys, and the Files API and Skills API exited beta across the SDKs. Service account keys are the practical unlock for anyone who has been running production traffic on a named employee’s key and knew it was wrong.
- Personal keys and service account keys in Console
- Files API out of beta across SDKs
- Skills API out of beta across SDKs
Model Hardware Standard August 27 research preview
Anthropic published “Previewing the Model Hardware Standard” on August 27, 2026. It is a research preview rather than a shipped requirement, so nothing in your deployment changes today, but it is the kind of document an infrastructure or procurement team should read early rather than after it becomes a standard.
- A research preview, not a commitment
- Relevant to infrastructure and hardware planning
- Read it before it turns into a purchasing constraint
New betas worth knowing API
Three beta surfaces landed in this window. Per-message effort, behind the header mid-conversation-output-config-2026-07-01, is available on Fable 5.1, Mythos 5.1 and Opus 5, and lets a single conversation move up and down the effort ladder instead of committing at the first turn. Turn-scoped system messages narrow a system instruction to one turn. And thinking.display: "updates" changes how reasoning is surfaced. All three are beta: regression-test before any of them sits in a critical path.
- Per-message effort on Fable 5.1, Mythos 5.1 and Opus 5
- Turn-scoped system messages
thinking.display: "updates"- Beta surfaces move; pin and re-test
Claude for Teachers Free access
Verified US K-12 educators get free premium access. Sign-up is open through June 30, 2027.
- Announced July 14, 2026
- Verification required
- A recruiting channel as much as a product
Self-serve HIPAA Enterprise and Platform
HIPAA configuration became self-serve for Enterprise and Platform customers on July 14, 2026, removing a manual step from healthcare deployments. Read it beside the 5.1 retention requirement before assuming the two compose.
- Configure without a bespoke process
- Still requires your own compliance review
- Confirm scope before moving regulated data
Claude Tag Team beta
A shared Claude teammate inside selected Slack channels, with channel-scoped context, tools, memories, budgets and audit logs.
- Team and Enterprise beta
- Shared channel continuity
- Administrative spend and permission controls
Claude Science Specialist workbench
A customizable scientific environment with tools, packages, compute and auditable artifacts. The new Life Sciences Verification Program sits next to it as the access route to Mythos 5.1 for vetted life scientists.
- Research-oriented execution
- Transparent artifacts
- A sign of domain-specific workbenches to come
Agent governance controls August 7
A cluster of controls shipped on August 7, 2026: session budgets for Claude Managed Agents, advisor configuration, inference geo controls and Skills loading from GitHub. Read together, they answer the three questions procurement asks about agents: what can it spend, what steers it, and where does the inference happen.
- Session budgets cap agent spend rather than account spend
- Inference geo controls matter for data-residency commitments
- Skills loading from GitHub makes reusable behavior reviewable in source control
The text watermark, explained August 14
Anthropic published “How Claude’s text watermark works” on August 14, 2026. If your organization has a policy on AI-generated text disclosure, or contracts that turn on provenance, this is the document to read before the policy is drafted rather than after.
- Relevant to disclosure and provenance policy
- A vendor description of its own mechanism, not an independent audit
- Test what your own downstream tooling preserves
Claude is now a family of work surfaces
Choosing Claude is no longer just choosing a model. The decisive question is where the work should run: conversation, terminal, governed desktop workspace, team channel, design surface or business application.
| Surface | Best for | Context advantage | Primary caution |
|---|---|---|---|
| Claude chat | Analysis, writing, research and files | Conversation, uploads, connectors and memory | Large context still needs coverage checks |
| Claude Code | Repository-scale engineering | Codebase, terminal, tools and project instructions | Command and prompt-injection risk |
| Claude Cowork | Desktop knowledge work | Selected folders, local apps, skills and plugins | Mount permissions and action review |
| Claude Tag | Shared team delegation | Channel history, scoped tools and shared memory | Spend, permissions and public mistakes |
| Claude Design | Rapid visual exploration | Brand inputs, conversation and prototypes | Still a Labs product; professional finishing required |
| Claude Science | Auditable scientific work | Packages, tools, compute and artifacts | Expert validation remains essential |
From source material to finished work without changing context
Anthropic’s direction is clear: Claude should follow the work across files, applications and teams instead of making users rebuild the brief in every surface.
Claude Code
Plans, edits, tests and debugs inside the real repository.
- Agent teams and subagents
- Long-running workflows
- Code review and verification
Claude Cowork
Runs multi-step tasks against selected desktop files and applications.
- Read-only or controlled write modes
- Reusable skills and plugins
- Dispatch from text or voice
Excel, PowerPoint and Word
Claude works directly in business documents and carries context between applications. Write tools shipped on July 7, 2026: Claude can draft and send email, act on the calendar and create or update files.
- Model, audit and explain spreadsheets
- Build decks from live analysis
- Review write permissions before granting them
Claude Tag
A shared team agent in Slack with scoped identity and memory.
- Channel-specific access
- Shared continuation
- Logs and budget controls
Claude Design
Explores prototypes and polished visual directions through conversation.
- Software experience ideation
- Slides and one-pagers
- Canva handoff
MCP and apps
Pulls live context from enterprise and creative systems.
- Google Drive and Gmail
- Market and portfolio data
- Blender and specialist tools
Skills and plugins
Packages instructions, tools and workflows into repeatable organizational capability. The Skills API left beta across the SDKs on August 27, 2026.
- Reduce prompt folklore
- Standardize recurring work
- Deploy domain templates
Memory and context
Carries relevant context across sessions and, increasingly, across applications. On July 10, 2026 memory was reworked into individual categorized entries, replacing the daily memory summary.
- Preserve audience and standards
- Inspect and remove entries one at a time
- Review what should persist
Claude is becoming useful before, during and after the creative tool
Claude does not replace taste. Its advantage is expanding the number of directions a creative team can explore, automating repetitive production and keeping strategy connected to the artifact.
Claude Design Labs
Explore software experiences, prototypes, slides and one-pagers with visual iteration inside the conversation.
- Start with audience and desired behavior
- Include brand rules and references
- Export into professional finishing tools
Creative connectors MCP
Claude can work with tools such as Blender through connectors, scripts and the application’s own APIs.
- Analyze and debug scenes
- Batch repetitive changes
- Create custom tools inside the creative application
Cross-format production
Claude can turn research into a document, document into deck, data into charts and creative brief into a buildable prototype.
- Keep one narrative thread
- Reduce manual reformatting
- Use humans for taste and final selection
Build three distinct directions for this onboarding flow. Use our brand system, explain the behavioral idea behind each route, and make every prototype testable rather than decorative.
Inspect this Blender scene and identify the repetitive production steps. Propose a reversible automation plan, then implement only the steps I approve.
Turn this research and workbook into a 12-slide executive deck. Use the approved master, keep one claim per slide, and link every chart to its source.
Do not redesign this. Review it as a creative director: identify where the execution departs from the stated concept, audience or brand behavior.
Eight habits that make Claude substantially better
The model upgrade matters, but workplace behavior determines whether that capability becomes useful, expensive or risky.
Front-load the context
Give Claude the complete source pack and explain how the files relate before asking for conclusions.
Let it inspect the brief
Ask what is missing or inconsistent before it begins production.
Choose effort deliberately
Use lower effort for reversible work and escalate only when consequence justifies it. On 5.1, adaptive thinking is always on, so effort is the only lever left.
Define completion
Specify the artifact, validation criteria and evidence report, not only the topic.
Keep context across stages
Move from analysis to file to deck without rebuilding the narrative in a new chat.
Use an adversarial second pass
Ask Claude to identify the weakest claims, broken assumptions and missing tests in its own work.
Name the audience and stakes
Claude changes depth, tone and caution when it knows who will use the result and what failure costs.
Trust the loop, inspect the result
Avoid micromanaging every step, but review commands, diffs, formulas and finished artifacts.
Produce the completed board memo, not an outline. Validate every recommendation against the attached evidence and include a one-page appendix of unresolved assumptions.
Add pagination to the users API, update the contract and documentation, add edge-case tests, run the full suite, and stop only when CI passes or you can name the blocker precisely.
Re-read your work as a skeptical domain expert. Identify the three conclusions most likely to be wrong and show what evidence would change each one.
Before synthesizing, create a coverage map of every supplied document. After the answer, list any sources or sections you did not materially use.
The more Claude can act, the more its environment matters
Agent capability changes the failure mode. A weak chat answer is inconvenient; a tool-using agent with broad file and network access can create real operational damage. This edition adds a second category: a model generation that fails requests your current code makes legally today.
Three breaking changes on 5.1
Moving traffic to claude-fable-5-1 or claude-mythos-5-1 can break working code in three ways. tool_choice types any and tool return a 400. Replaying a thinking block after a changed system prompt, tools or message returns a 400 on accounts created on or after August 31, 2026, controlled by the thinking-binding-controls-2026-08-01 beta header. And both models require 30-day retention, so a zero data retention account may not be permitted to call them at all. Test all three before you switch a model id in production.
Zero data retention is a hard gate on 5.1
If your agreement with Anthropic includes zero data retention, Fable 5.1 and Mythos 5.1 are not available to you unless Anthropic authorizes an exception. This is not something a configuration flag fixes. Raise it with your account team before an evaluation is scheduled, not after a pilot has been designed around the model.
Prompt injection
Instructions inside email, documents, websites or pasted prompts can redirect an agent. Treat external content as untrusted input.
Mount and write access
Cowork permissions should match the task. Read-only, read-write and no-delete boundaries are meaningful controls.
Higher effort cost
More reasoning can improve hard work but adds latency, token use and the possibility of unnecessary exploration. On 5.1 you cannot turn thinking off at all.
Preview instability
Dynamic workflows, Labs products and beta surfaces require regression testing before production use. Per-message effort, turn-scoped system messages and the updates thinking display are all beta.
Long context omissions
A 1M-token window is capacity, not proof of complete recall or equal attention. That is now the default window on 5.1 rather than an opt-in, so the coverage discipline applies to every call.
No native media generation
Claude can plan, analyze and prototype visuals, but final image, video and audio generation still depends on other tools.
Model-version drift
A model upgrade can change formatting, tool choices and reasoning style. Re-test critical prompts and workflows.
Diplomatic language
Claude may soften criticism unless directness is explicitly requested. Ask for the harshest defensible review.
Opus 4.1 is gone
On Anthropic’s deprecations page, checked September 3, 2026, claude-opus-4-1-20250805 shows status Retired with the line “This model was retired August 5, 2026.” Anything still pinned to the 4.1 identifier, an integration, a saved evaluation or a scheduled job, is failing now as a request error rather than a warning. The replacement was claude-opus-4-8. If you have not hit the error yet, that tells you the pinned job is not running, which is its own finding.
An empty retirement calendar was never empty
The claim that no Claude retirement is dated before November 30, 2026 held only for deprecated models. Three Active models carry a tentative retirement floor inside that window: claude-sonnet-4-5-20250929 not sooner than September 29, 2026, claude-haiku-4-5-20251001 not sooner than October 15, 2026, and claude-opus-4-5-20251101 not sooner than November 24, 2026. A floor is not an announcement, but it is also not nothing, and reading the deprecations table as a list of dated retirements misses it entirely.
Python SDK v1.0 will stop a build
The August 20, 2026 release moves httpx to httpx2, requires Python 3.10 or later, removes Text Completions and removes temperature, top_p and top_k from Messages. An unpinned dependency will pick this up on its own schedule, which is rarely yours.
The Workbench URL is dead
The legacy Workbench at platform.claude.com/workbench sunset on August 17, 2026 and the replacement Playground at platform.claude.com/playground was documented in the August 18, 2026 release note. Three experimental /v1/experimental/*_prompt endpoints retired on the same August 17 date. Internal links, onboarding docs and screenshots will still point at the old surface.
July 24 breaking changes still apply
Setting thinking to disabled is only valid at effort high or below; combining it with extra high or max returns a 400. Requesting fast speed on Opus 4.7 errors. Both break working integrations silently until a call fails.
Shifting defaults you cannot currently verify
The July 24 announcement put Opus 5 as the Claude Max default and left Sonnet 5 on Free and Pro. Neither has been re-verifiable since August 19, 2026, because anthropic.com/pricing returns a 403 and no readable page restates the per-plan defaults. Opus 4.8’s legacy label is unconfirmed for a related reason: the heading exists but its body is JavaScript-rendered and came back empty. Pin a model in anything you evaluate, or your baseline changes underneath the test.
The safety fallback has no published name
Anthropic says dual-use cybersecurity work is redirected “to our Opus models,” plural and unnamed, naming penetration testing, exploit generation and binary-based vulnerability scanning as examples. No first-party page names a specific fallback model. If a runbook, an incident playbook or a user-facing message in your product names one, it is repeating an inference rather than a documented fact.
Vendor benchmark claims
The positioning of Fable 5.1 and Mythos 5.1 as the world’s most advanced models for coding and knowledge work is Anthropic’s own, as is the 0.5% gap between Opus 5 and Fable 5. Run a task-level evaluation before moving production work up or down a price tier on the strength of it.
| Environment | Useful boundary | What still requires review |
|---|---|---|
| Claude chat | Ephemeral server-side container | Files produced, connector scope and claims |
| Claude Code | Local sandbox plus human command approvals | Shell commands, diffs, secrets and outbound access |
| Claude Cowork | Sealed VM and selected folder mounts | Mounted workspace, MCP servers and completed actions |
| Claude Tag | Channel-scoped tools, memory and spend | Public responses, tool actions and cross-team access |
First-party evidence behind this guide
Product status, availability and pricing can change quickly. These are the primary Anthropic pages checked for this edition, verified September 3, 2026. Four caveats about coverage. First, two claims could not be re-verified and are marked unconfirmed on the page rather than quietly repeated: Opus 4.8’s legacy label, because the models overview renders that section in JavaScript and returned an empty body, and the per-plan defaults, because anthropic.com/pricing returned a 403. Second, a large group of operational items here comes from Anthropic’s rolling release notes rather than a dated article: the August 17 Workbench sunset and the August 18 Playground rename, the August 20 Python SDK v1.0 release, the August 26 Compliance API and Admin API changes, the August 27 Console key and Files and Skills API changes, the per-message effort, turn-scoped system message and thinking-display betas, and the Sonnet 5 pricing confirmation. Release notes are rewritten in place and cannot anchor a dated claim, so they are not listed below and a reader relying on any of them should confirm it directly. Third, the two Anthropic sources describing access to Mythos 5.1 frame it differently, through the verification programs and through Project Glasswing, and this guide reports both rather than picking one. Fourth, the Frontier Red Team’s July 30, 2026 cybersecurity write-up is safety research with no pricing or model implications; nothing here rests on it, so it is not cited.
AI Mindset