Claude 4 refers to Anthropic's fourth major model generation — the Claude 4.x series including Opus 4.6, Sonnet 4.6, and Haiku 4.5.

Tag: AI Models 2026

Claude Cowork Not Working: 5 Common Errors and Fixes

Last refreshed: June 9, 2026

Claude AI · Tygart Media

Most common cause: The Cowork VM disk is full (sessiondata.img). Second most common: a scheduled task depends on a local process that stops when your machine sleeps. Both are fixable in minutes.

Claude Cowork stops working for a small set of predictable reasons. This page covers the five most common failures, how to diagnose which one you’re hitting, and the exact fix for each.

Claude Cowork Error Quick-Reference

Claude Cowork issues: quick diagnosis

Symptom	Most likely cause	Fix
Cowork won’t launch	App update pending	Quit Claude desktop app, reopen — auto-updates on restart
MCP tools not showing	MCP server not running or config error	Check claude_desktop_config.json syntax; restart app
“Not connected” in Cowork panel	Plugin not loaded or credentials expired	Re-authenticate the plugin from Settings > Capabilities
Skills not triggering	Skill description doesn’t match your prompt	Use the exact trigger phrase from the skill description
File tools not working	No folder selected	Select a working folder via the folder icon in Cowork
Scheduled tasks not running	Claude desktop app not running at scheduled time	Keep app running in background; check task log for errors
Computer use not responding	Permission not granted for target app	Claude will prompt for permission — approve in the dialog

Symptom	Most Likely Cause	Fix
Cowork won’t start / hangs on launch	Cowork VM disk full (sessiondata.img)	Clear sessiondata.img or expand VM disk allocation
Scheduled tasks stop running overnight	Local process killed when machine sleeps	Use GCP Cloud Run cron instead of local scheduler
Tool calls return empty responses	MCP server disconnected	Restart Claude Desktop; re-authenticate MCP servers
File edits not saving	Workspace folder not mounted	Reconnect folder via Cowork settings
Browser automation stops mid-task	Chrome extension lost connection	Reload extension; check tab is in allowed group

Claude Cowork Error Quick-Reference

Symptom	Most Likely Cause	Fix
Cowork won’t start / hangs on launch	Cowork VM disk full (sessiondata.img)	Clear sessiondata.img or expand VM disk allocation
Scheduled tasks stop running overnight	Local process killed when machine sleeps	Use GCP Cloud Run cron instead of local scheduler
Tool calls return empty responses	MCP server disconnected	Restart Claude Desktop; re-authenticate MCP servers
File edits not saving	Workspace folder not mounted	Reconnect folder via Cowork settings
Browser automation stops mid-task	Chrome extension lost connection	Reload extension; check tab is in allowed group

Claude Cowork Error Quick-Reference

Symptom	Most Likely Cause	Fix
Cowork won’t start / hangs on launch	Cowork VM disk full (sessiondata.img)	Clear sessiondata.img or expand VM disk allocation
Scheduled tasks stop running overnight	Local process killed when machine sleeps	Use GCP Cloud Run cron instead of local scheduler
Tool calls return empty responses	MCP server disconnected	Restart Claude Desktop; re-authenticate MCP servers
File edits not saving	Workspace folder not mounted	Reconnect folder via Cowork settings
Browser automation stops mid-task	Chrome extension lost connection	Reload extension; check tab is in allowed group

Error 1: “useradd failed: exit status 12”

What it means: The Cowork VM’s internal disk (sessiondata.img) is full. No new sessions can be provisioned.

Fix: Quit Claude Desktop. Move sessiondata.img from %APPDATA%\Claude\vm_bundles\claudevm.bundle\ (Windows) or ~/Library/Application Support/Claude/vm_bundles/claudevm.bundle/ (macOS) to your Desktop. Relaunch Claude Desktop — it recreates a fresh image. Full walkthrough: Claude Cowork useradd Failed Error Fix.

Error 2: Scheduled Tasks Stop Running

What it means: Tasks that were running on schedule suddenly stop firing. Often appears as tasks last running a few days ago with no new entries.

Causes: Machine went to sleep, Claude Desktop was quit, or the local runner process died. Cowork tasks require Claude Desktop to be open and running on an active machine. They are not fully cloud-hosted — they depend on the local Cowork environment being live.

Fix: Reopen Claude Desktop and manually trigger one task to verify it runs. For tasks that need to run reliably without the machine being awake, move them to a GCP Cloud Run cron job or a cloud VM instead of Cowork’s local scheduler.

Error 3: MCP Tools Not Available in Cowork

What it means: Cowork tasks can’t access Notion, Gmail, or other connected services that work fine in Chat.

Fix: MCP servers must be configured in claude_desktop_config.json — the same config file Claude Desktop uses. If an MCP server appears in Chat but not in Cowork, verify it’s listed in the desktop config, not just the web interface. Restart Claude Desktop after any config changes.

Error 4: File Access Denied or Path Not Found

What it means: A Cowork task fails trying to read or write a file that should be accessible.

Fix: Cowork’s VM mounts specific directories from your machine. If the file is outside a mounted path, Cowork can’t reach it. Check that the file path is within your configured working directories. On Windows, path separator issues (\ vs /) inside the Linux VM can also cause this — use forward slashes or escape backslashes in task prompts.

Error 5: Tasks Run but Produce Wrong Output

What it means: Cowork is running but the results are stale, wrong, or missing context from previous runs.

Fix: Cowork tasks don’t have memory of previous runs by default. If your task depends on knowing what happened last time — what was published, what changed — you need to build that context explicitly into the task prompt, typically by reading a log from Notion or a local file at the start of each run. The task prompt is the only persistent instruction; Claude doesn’t remember prior task outputs.

Why did Cowork tasks stop running overnight?

Cowork requires Claude Desktop to be running on an active machine. If your computer slept, hibernated, or Claude Desktop was closed, scheduled tasks won’t fire. For always-on reliability, route tasks through a cloud runner instead.

Why can Cowork not find my files?

Cowork’s Linux VM only has access to directories you’ve configured as mount points. Files outside those paths are invisible to the VM. Verify your working directory configuration in Claude Desktop settings.

Does Cowork work on Windows?

Yes, Cowork is available on both Windows and macOS via Claude Desktop. The VM behavior and file paths differ slightly between platforms but the core functionality is the same.

Frequently Asked Questions

Why does Claude Cowork stop working when my computer sleeps?

Claude Cowork scheduled tasks depend on a local process that gets killed when your machine sleeps or the lid closes. The fix is to run scheduled tasks via GCP Cloud Run or another always-on host rather than relying on the local Cowork scheduler.

How do I fix the Cowork VM disk full error?

The most common Cowork failure is a full sessiondata.img file on the Cowork VM. Open the VM settings, clear sessiondata.img or increase the disk allocation. This resolves the majority of ‘Cowork won’t start’ issues.

Why are my Claude Cowork MCP tools returning empty responses?

Empty MCP tool responses usually mean the MCP server has disconnected. Restart Claude Desktop and re-authenticate the affected MCP servers through Settings > Capabilities. If the issue persists, check that the MCP server process is still running.

Is Claude Cowork the same as Claude in Chrome?

No. Claude Cowork is a desktop agent for file management and task automation. Claude in Chrome is a browser extension that gives Claude control of your active Chrome tab. They are separate tools that can be used together but serve different purposes.

What should I do if Claude Cowork file edits aren’t saving?

If file edits aren’t saving, the workspace folder is likely not properly mounted. Go to Cowork settings and reconnect the folder. Make sure you’ve granted Cowork write access to the directory, not just read access.

Frequently Asked Questions

Why is Claude Cowork not working?

The most common reasons Claude Cowork stops working are: (1) a pending app update — quit and reopen the Claude desktop app to apply updates; (2) an MCP server configuration error — check your claude_desktop_config.json for syntax issues; (3) expired plugin credentials — re-authenticate from Settings > Capabilities; (4) no working folder selected — click the folder icon in the Cowork panel to select one. Most Cowork issues resolve with an app restart.

How do I fix MCP tools not showing in Claude Cowork?

If MCP tools are not appearing in Cowork, check three things: (1) your claude_desktop_config.json file has valid JSON syntax — a single missing comma breaks the entire config; (2) the MCP server command is correct and the binary or package is installed; (3) you restarted the Claude desktop app after editing the config. Use ‘claude mcp list’ in your terminal to verify which servers are loaded. If a server shows as loaded but tools don’t appear, the server may be failing silently — check its logs.

Why are my Cowork skills not triggering?

Skills trigger based on the description and trigger phrases in their SKILL.md. If a skill isn’t firing, check that your prompt closely matches the trigger language in the skill description. Skills are loaded by Claude based on semantic matching — if your prompt is ambiguous, Claude may not recognize which skill to invoke. Try using the exact trigger phrase listed in the skill’s description. You can view installed skills in Settings > Capabilities > Skills.

Why did Claude Cowork stop working after an update?

App updates occasionally reset plugin configurations or require re-authentication. After a Claude desktop app update: (1) re-open the Cowork panel; (2) check if any plugins show ‘reconnect’ prompts in Settings > Capabilities; (3) verify your MCP servers are still listed in claude_desktop_config.json — updates don’t modify this file, but a fresh install might. If a plugin stopped working, re-authorize it from Settings.

How do I select a working folder in Claude Cowork?

Click the folder icon in the Cowork panel header to open the folder picker. Select the directory you want Claude to read from and write to. Without a selected folder, file tools (Read, Write, Edit) won’t have access to your files. The selected folder path persists across sessions. You can change it at any time by clicking the folder icon again.

What should I do if Claude Cowork computer use isn’t responding?

Computer use in Cowork requires explicit permission for each application. When Claude needs to control an app, it will show a permission dialog — you must approve it before Claude can interact with that app. If the permission dialog doesn’t appear, try re-stating your request. If computer use worked before but stopped, check that the target application hasn’t been updated or moved. Browsers (Chrome, Edge, Safari) are read-only in computer use — for browser automation, use the Claude in Chrome extension instead.

📖 Related Claude Guides

April 16, 2026

Claude Cowork vs Claude Chat: When to Use Which

Last refreshed: May 15, 2026

Model Accuracy Note — Updated May 2026

Current flagship: Claude Opus 4.7 (claude-opus-4-7). Current models: Opus 4.7 · Sonnet 4.6 · Haiku 4.5. Claude Opus 4.7 (claude-opus-4-7) is the current flagship as of April 16, 2026. Where this article references Opus 4.6 or earlier models, those references are historical. See current model tracker →. See current model tracker →

Claude AI · Tygart Media

Quick answer: Use Cowork for scheduled, recurring, or multi-step tasks that need to persist and run on their own. Use Claude Chat for interactive work, analysis, writing, and one-off tasks you’re doing right now.

Anthropic now offers two distinct modes of working with Claude — the familiar chat interface and Cowork, a persistent task and agent environment. They look similar but serve fundamentally different purposes. Using the wrong one creates friction; knowing which to reach for first saves significant time.

What Cowork Actually Is

Cowork is a persistent agent environment inside Claude Desktop. It gives Claude access to your local filesystem, a sandboxed Linux VM with bash execution, your installed MCP servers, and a scheduler. Tasks you set up in Cowork can run on a schedule — daily, weekly, whenever you trigger them — without you being in the conversation. Claude operates autonomously against your instructions until the task is done.

What Claude Chat Actually Is

Claude Chat (claude.ai or the Claude app) is a stateless, interactive conversation interface. Each session is fresh. Claude has no persistent memory across sessions beyond what you’ve configured in memory settings. It’s optimized for real-time back-and-forth: you ask, Claude responds, you refine. The bash environment in Chat (used for file operations and code execution) is sandboxed and resets between sessions.

Side-by-Side Comparison

Factor	Claude Chat	Claude Cowork
Runs without you	No	Yes — scheduled tasks
Access to your files	Upload only	Direct filesystem access
Persistent across sessions	No (memory only)	Yes — tasks and state persist
Best for	Interactive work, writing, analysis	Recurring automation, pipelines
MCP tool access	Yes (if configured)	Yes + local filesystem tools
Runs on	Anthropic’s cloud	Your local machine
Resource competition	None (cloud-side)	Shares your CPU/disk
Skill files	Yes (/mnt/skills/)	Yes (same mount)

When to Use Claude Chat

Chat is the right tool when you’re actively involved in the work — drafting, editing, analyzing, strategizing. If you need to go back and forth, refine an output, or make judgment calls mid-task, Chat’s interactive model is faster and more natural. It’s also better for any task that’s genuinely one-off: you do it once, you’re done, there’s nothing to schedule or automate.

Chat also runs in the cloud, meaning it doesn’t compete with your machine’s other processes and doesn’t run into the local VM disk limitations that Cowork can hit with heavy workloads.

When to Use Cowork

Cowork shines for work that should happen without you: daily newsroom publishing, weekly SEO reports, nightly data syncs, any pipeline that follows the same steps every run. If you find yourself doing the same Claude Chat session more than twice a week, it’s a candidate for a Cowork task.

Cowork also makes sense for tasks that need direct access to files on your machine — reading from a local folder, processing downloads, interacting with local applications — since Chat requires you to explicitly upload files each session.

Known Cowork Limitation to Be Aware Of

Cowork runs on a local VM (the sessiondata.img file) with a fixed 8.5GB disk. Heavy users with many skills installed will periodically hit a disk-full error that prevents new sessions from launching. This is a known bug (GitHub #30751) with a manual workaround. See Claude Cowork useradd Failed Error: How to Fix It for the fix.

Is Claude Cowork better than Claude Chat?

Neither is better — they serve different purposes. Chat is optimized for interactive, real-time work. Cowork is for persistent, scheduled, autonomous tasks. Most power users use both regularly for different types of work.

Can Claude Cowork access the internet?

Yes, through MCP server integrations and web search tools. Cowork tasks can call APIs, search the web, read from connected services like Notion or Gmail, and interact with any MCP-connected tool you’ve configured.

Does Claude Cowork use the same AI model as Chat?

Yes — Cowork uses the same underlying Claude models (currently Opus 4.6 and Sonnet 4.6). The difference is the execution environment, not the model.

April 16, 2026

Claude Cowork ‘useradd Failed’ Error: How to Fix the sessiondata.img Full Bug

Last refreshed: May 15, 2026

Claude AI · Tygart Media

⚠ Known Bug: This is GitHub issue #30751 — still open as of April 2026. Anthropic has not shipped a permanent fix. The workaround below is the only reliable solution.

If every Cowork task is failing with useradd: cannot create directory /sessions/friendly-youthful-thompson or a similar error, your Cowork VM’s internal disk is full. This is not something you broke — it’s a known Anthropic bug that affects power users consistently. Here’s exactly what’s happening and how to fix it in under two minutes.

What’s Causing the Error

Cowork runs on a local VM with a fixed 8.5GB disk image called sessiondata.img. Every Cowork conversation creates a new directory under /sessions/<name>/ inside that VM and caches all your installed plugins and skills there. Those directories are never cleaned up automatically. Once the disk fills — roughly 80 sessions for light users, 40–50 sessions for users with many skills installed — every new task fails immediately with a useradd error. The session simply can’t be provisioned.

If you have 20+ skills installed (the Tygart Media stack runs 40+), you’ll hit the cap significantly faster than the average user.

The Fix: Move the Image File

The fix is the same on macOS and Windows: move sessiondata.img out of its location so Claude Desktop rebuilds it fresh on next launch.

Windows

Quit Claude Desktop completely. Open Run (Win + R), paste this path and press Enter:

%APPDATA%\Claudem_bundles\claudevm.bundle\

Find sessiondata.img and move it to your Desktop as a backup. Relaunch Claude Desktop — it will recreate a fresh image automatically. Your first Cowork session after the reset may take slightly longer while plugins reinstall.

macOS

Quit Claude Desktop. In Finder, press Cmd + Shift + G and go to:

~/Library/Application Support/Claude/vm_bundles/claudevm.bundle/

Move sessiondata.img to your Desktop. Relaunch Claude Desktop.

What Gets Wiped vs What’s Preserved

Data	Location	Wiped?
Sidebar task list	Electron IndexedDB	✅ Preserved
Scheduled task definitions	Documents/Claude/Scheduled/	✅ Preserved
MCP server config	claude_desktop_config.json	✅ Preserved
Chat conversation history	Electron LevelDB	✅ Preserved
VM plugin/skill cache	Inside sessiondata.img	⚠ Wiped (auto re-downloads)
VM session working dirs	/sessions/<n>/ inside VM	⚠ Wiped (this is the fix)

How Often Will You Need to Do This?

Until Anthropic ships automatic session cleanup, this is a recurring task. With a heavy skill load, plan on running the fix every 4–6 weeks or whenever you see the useradd error return. Setting a calendar reminder is the most reliable approach.

The Longer-Term Fix: Move Heavy Operations Off Cowork

The root cause is that Cowork was designed for lighter, conversational task automation — not running dozens of skills across many parallel sessions. If you’re running content pipelines, batch WordPress operations, or multi-step automation workflows, moving those operations to a GCP Cloud Run cron job or Compute Engine VM eliminates the local VM bottleneck entirely. Cowork’s local sandbox competes for your machine’s resources; GCP runs isolated, always-on, and never fills up your laptop’s disk.

Why does Cowork say “useradd failed: exit status 12”?

The Cowork VM’s internal disk (sessiondata.img) is full. It can no longer create new session user directories. Moving the image file out and letting Claude Desktop recreate it clears the disk and resolves the error.

Will I lose my Cowork tasks if I move sessiondata.img?

No. Your task definitions, scheduled tasks, MCP config, and conversation history are all stored outside the VM image. Only the internal plugin/skill cache is wiped — it re-downloads automatically on the next session.

How do I prevent Cowork from filling up again?

Until Anthropic ships a permanent fix (GitHub issue #30751), the options are: run the reset script periodically, reduce your installed skill count, or route heavy operations to GCP instead of Cowork.

April 16, 2026

Claude 5 Release Date 2026: Leak Signals, Expected Features & Anthropic’s Timeline

Updated June 10, 2026

The “Claude 5” question now has an answer: Anthropic’s next-generation model shipped as Claude Fable 5, a new tier above Opus rather than a “Claude 5” rename. As of June 10, 2026, Anthropic’s current lineup is Claude Fable 5 (the new top tier above Opus, $10 input / $50 output per MTok), Opus 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5). Full details: the Claude Fable 5 Complete Guide.

Last refreshed: June 9, 2026

Verified vs. reported — May 15, 2026 standard: This article tracks third-party reporting on Claude 5’s expected release window and features. As of May 15, 2026, Anthropic has not, to our review of anthropic.com/news and docs.claude.com, published an official Claude 5 launch announcement. The Q2 2026 timeline, ~90%+ SWE-bench Verified figure, 500K context window claim, and “Sonnet 5 / Fennec” codename references all trace to third-party reporting (TechCrunch interview citations, Claude5.com, Fello AI, WaveSpeed Blog) that we could not independently confirm against an Anthropic-published primary source. The information may still be accurate; the verified-vs-reported distinction means it has not been confirmed by Anthropic on the record.

For the full current model lineup that is officially documented — Opus 4.8 (knowledge cutoff January 2026, 1M context, $5/$25 MTok), Sonnet 4.6, Haiku 4.5 — see Claude Models Roadmap May 2026. That article maintains the verified-vs-reported standard throughout.

Model Accuracy Note — Updated June 9, 2026

Current flagship: Claude Opus 4.8 (claude-opus-4-8). Current models: Opus 4.8 · Sonnet 4.6 · Haiku 4.5. Claude Opus 4.6 referenced in this article has been superseded. See current model tracker →

Claude AI · Tygart Media · Updated April 2026

Current status (April 16, 2026): Claude 5 has not been officially announced by Anthropic. The current latest models are Claude Opus 4.6 and Claude Sonnet 4.6, released in February 2026. Based on Anthropic’s release cadence and early signals, Claude 5 is expected Q2–Q3 2026.

Every few months, a new wave of “Claude 5 release date” searches spikes — and it makes sense. Anthropic moves fast, the gaps between major generations have been shortening, and early signals like Vertex AI log leaks have given the community something to speculate on. Here’s an honest breakdown of what’s confirmed, what’s leaked, and what the pattern suggests.

Claude 5 Expected Specs vs Current Models (June 2026)

Attribute	Claude Opus 4.8 (Current)	Claude 5 (Rumored)
Release window	Available now	Late 2026 (unconfirmed)
Context window	1M tokens	2M+ tokens (speculated)
Multimodal	Text + vision	Text + vision + audio (rumored)
Flagship API price	$5 input / $25 output per MTok	Unannounced
Reasoning	Strong	Improved extended thinking (speculated)

Claude 5 specs are unconfirmed as of June 9, 2026. All information is based on industry signals and Anthropic research publications — not official announcements.

What’s Confirmed About Claude 5

As of April 2026, Anthropic has not officially announced Claude 5 by name in any public release notes, API documentation, or blog post. The company’s official model table shows the Claude 4.x family as current. No countdown page exists. No API model string beginning with claude-5 has appeared in public documentation.

What is confirmed: Anthropic is actively deprecating the original Claude 4.0 models (retiring June 15, 2026), recommending migration to Claude Sonnet 4.6 and Opus 4.6. This is a routine generational housekeeping move, not a Claude 5 announcement.

The Evidence For a Q2–Q3 2026 Release

The strongest early signal came in early February 2026, when a model identifier — claude-sonnet-5@20260203 — appeared briefly in Google Vertex AI error logs. Independent sources cross-verified the leak, and the codename “Fennec” circulated alongside claimed benchmark scores of around 80.9% on SWE-bench Verified, compared to Opus 4.6’s current scores.

Beyond the leak, the pattern is consistent: Anthropic has released a new major model generation roughly every 12–14 months since Claude 3. Claude 4.5 (the highest-capability 4.x model) reached 77.2% on SWE-bench Verified. A Claude 5 release that clearly exceeds that — not just marginally — would justify a major version bump and align with Anthropic’s stated commitment to releasing models that represent genuine capability leaps, not incremental updates.

Anthropic’s Release Pattern

Generation	Initial Release	Gap to Next Major
Claude 2	July 2023	~8 months
Claude 3	March 2024	~14 months
Claude 4	May 2025	~12–14 months → Q2–Q3 2026

A 12-month gap from the Claude 4 launch (May 2025) points to May–July 2026 as the earliest likely window. Anthropic has been explicit that they won’t rush a release — Claude 5 would need to clearly establish a new capability tier to justify the version number.

What Claude 5 Is Expected to Improve

Based on leaked benchmark data and Anthropic’s public research direction, the Claude 5 generation is expected to push forward on: extended thinking and multi-step reasoning (building on the chain-of-thought work in Claude 3.5+), larger context handling, improved agentic reliability for long-horizon tasks, and faster inference at the Sonnet tier. Pricing is expected to follow the established pattern — Claude 5 Sonnet likely priced at or below current Opus 4.6 rates while outperforming it on most tasks.

The Current Models Are Excellent — Don’t Wait

If you’re evaluating whether to build on Claude now or wait for Claude 5, the answer is build now. Claude Sonnet 4.6 and Opus 4.6 are capable, stable, and well-documented. The 4.x API will remain live well after Claude 5 launches — Anthropic maintains parallel model availability for enterprise predictability. Waiting costs you months of production time for a model that may arrive on an uncertain schedule.

For current model specs and API strings, see Claude API Model Strings — Complete Reference. For pricing on current models, see Claude AI Pricing: Every Plan Explained.

When is Claude 5 coming out?

Claude 5 has not been officially announced. Based on Anthropic’s release cadence and early Vertex AI log leaks, Q2–Q3 2026 (roughly May–September) is the most cited window. No confirmed date exists as of April 2026.

Is Claude 5 confirmed?

No. Anthropic has not officially announced Claude 5 by name. The “Fennec” codename and claude-sonnet-5@20260203 model string surfaced in third-party Vertex AI logs, but Anthropic has not confirmed a Claude 5 release.

What is the latest Claude model right now (April 2026)?

The current latest Claude models are Claude Opus 4.6 (claude-opus-4-8) and Claude Sonnet 4.6 (claude-sonnet-4-6), both released in February 2026. Claude Haiku 4.5 is the current speed/cost tier.

Will Claude 5 Sonnet beat Claude Opus 4.6?

That’s the expected pattern. With every prior generation, the mid-tier Sonnet model of the new generation outperformed the previous generation’s Opus on most benchmarks, at lower cost. Leaked benchmark data suggests Claude 5 Sonnet (“Fennec”) scores around 80.9% on SWE-bench Verified versus Opus 4.6’s current scores.

When will Claude 5 be released?

Anthropic has not officially announced a Claude 5 release date as of June 2026. Industry analysts and leak signals suggest a potential release in late 2026, but Anthropic typically announces model releases a few weeks before availability. The current flagship is Claude Opus 4.8 (claude-opus-4-8), released in 2026.

What features will Claude 5 have?

No official feature list exists for Claude 5. Based on Anthropic’s research publications and the pattern of Claude 4 improvements, Claude 5 is expected to improve reasoning, extended context handling, and multimodal capabilities. Any specific feature claims circulating online are speculation unless sourced directly from Anthropic.

Should I wait for Claude 5 or use Claude Opus 4.8 now?

Use Claude Opus 4.8 now. It is the current flagship with 1M token context, strong reasoning, and available today at $5/$25 per million tokens. Waiting for an unannounced model means missing months of productivity. When Claude 5 launches, upgrading is straightforward — just swap the model ID in your API calls.

April 16, 2026

Claude 4 Deprecation: Sonnet 4 and Opus 4 Retire June 15, 2026

Last verified: June 13, 2026

Model Accuracy Note — Verified June 13, 2026

Retiring June 15, 2026: the original Claude Opus 4 (claude-opus-4-20250514) and Claude Sonnet 4 (claude-sonnet-4-20250514) — the May 2025 models. These are not Opus 4.6 or Sonnet 4.5, which remain active. Current models: Fable 5 · Opus 4.8 · Sonnet 4.6 · Haiku 4.5. Current model tracker →

Claude AI · Tygart Media

⚠ Deprecation Notice: Anthropic is retiring claude-sonnet-4-20250514 and claude-opus-4-20250514 — the original Claude 4.0 models from May 2025. API retirement is June 15, 2026. Migrate to Claude Sonnet 4.6 (claude-sonnet-4-6) and Claude Opus 4.8 (claude-opus-4-8).

If you are still running the original Claude Sonnet 4 or Opus 4 model strings in production, you have a hard deadline: June 15, 2026. After that date, calls to claude-sonnet-4-20250514 and claude-opus-4-20250514 return an error — there is no automatic failover to a newer model. Here is exactly what is retiring, what to migrate to, and the breaking changes to plan for.

Claude Model Lifecycle Status (June 2026)

Model	API ID	Status	Replacement
Claude Opus 4 (original)	claude-opus-4-20250514	⚠ Retires June 15, 2026	claude-opus-4-8
Claude Sonnet 4 (original)	claude-sonnet-4-20250514	⚠ Retires June 15, 2026	claude-sonnet-4-6
Claude Fable 5	claude-fable-5	✓ Current — top tier	—
Claude Opus 4.8	claude-opus-4-8	✓ Current Opus flagship	—
Claude Sonnet 4.6	claude-sonnet-4-6	✓ Current	—
Claude Haiku 4.5	claude-haiku-4-5	✓ Current	—

Alias trap: the dateless aliases claude-opus-4-0 and claude-sonnet-4-0 resolve to the retiring ...-20250514 snapshots — they go offline too. Claude Opus 4.6, Opus 4.7, Opus 4.5, and Sonnet 4.5 are separate, still-active models and are not affected by this retirement.

What’s Being Deprecated

Anthropic is retiring the original Claude 4.0 model versions — the ones that shipped in May 2025. These are distinct from the 4.x versions released since. The specific API strings going offline:

Model	API String (retiring)	Retirement Date
Claude Sonnet 4 (original)	`claude-sonnet-4-20250514`	June 15, 2026
Claude Opus 4 (original)	`claude-opus-4-20250514`	June 15, 2026

These are not the latest Claude 4 models. If you have been on Anthropic’s recommended alias endpoints, you are likely already on a current model. This deprecation primarily affects teams that pinned the specific 20250514 version strings in their API calls.

What to Migrate To

Anthropic’s recommended replacement within the same tier:

Retiring	Migrate To	API String
claude-sonnet-4-20250514	Claude Sonnet 4.6	`claude-sonnet-4-6`
claude-opus-4-20250514	Claude Opus 4.8	`claude-opus-4-8`

These are major upgrades, not just version bumps. Both current models ship a 1 million token context window at standard API pricing (no long-context premium), and the Opus line has advanced two full generations — 4.6, then 4.7, then 4.8 — since the original 4.0. For the most capable tier overall, Anthropic now offers Claude Fable 5 (claude-fable-5), a new tier that sits above Opus.

Breaking Changes When You Migrate

Moving off the original 4.0 strings is usually a model-ID swap, but the current models removed several request parameters. If you are jumping to Opus 4.8 or Fable 5, plan for these — each returns a 400 if left in:

Removed parameter	Replacement
`thinking: {type:"enabled", budget_tokens:N}`	Adaptive thinking — `thinking: {type:"adaptive"}` + `output_config.effort` (`low`/`medium`/`high`/`xhigh`/`max`)
`temperature` / `top_p` / `top_k`	Removed — steer behavior with prompting instead
Assistant-turn prefills (request ending on an `assistant` message)	Structured outputs — `output_config.format`

On Sonnet 4.6 and Opus 4.6 the fixed thinking budget is deprecated but still functional; on Fable 5, Opus 4.7, and Opus 4.8 it is fully removed. A global search for 20250514 in your codebase is the fastest way to find every call that needs changing.

How This Fits the Claude Model Timeline

Model	Released	Status
Claude Sonnet 4 / Opus 4 (original)	May 2025	⚠ Retire June 15, 2026
Claude Haiku 4.5	October 2025	✅ Current speed/cost tier
Claude Opus 4.6	February 2026	✅ Active (superseded by 4.8)
Claude Sonnet 4.6	February 2026	✅ Current production default
Claude Opus 4.8	2026	✅ Current Opus flagship
Claude Fable 5	2026	✅ Current top tier (above Opus)

What If You Don’t Migrate Before June 15?

API calls to claude-sonnet-4-20250514 or claude-opus-4-20250514 after June 15, 2026 will return errors. There is no automatic failover to a newer model — the call simply fails. If you have any production systems, scheduled jobs, or automated pipelines using these version strings, audit them now. A global search for 20250514 in your codebase is the fastest way to find your exposure.

What Comes After Claude 4.x

The “after” is already here. Since the original Claude 4.0 launched in May 2025, the Opus line has shipped 4.5, 4.6, 4.7, and now 4.8, and Anthropic introduced Claude Fable 5 as a new top tier above Opus. As of June 2026 there is no separately branded “Claude 5” generation; the cadence has been steady point releases within the 4.x Opus, Sonnet, and Haiku families, plus the new Fable tier. The practical takeaway: migrating off the retiring 4.0 strings puts you on models that are materially more capable, with a 1M-token context window as the new baseline.

Which Claude models retire on June 15, 2026?

The original Claude Sonnet 4 (claude-sonnet-4-20250514) and Claude Opus 4 (claude-opus-4-20250514), plus their dateless aliases claude-sonnet-4-0 and claude-opus-4-0. Opus 4.6, Opus 4.7, and Sonnet 4.5 are separate, still-active models and are not affected.

What should I migrate to from Claude Sonnet 4 and Opus 4?

Sonnet 4 migrates to claude-sonnet-4-6 (Claude Sonnet 4.6); Opus 4 migrates to claude-opus-4-8 (Claude Opus 4.8). Both ship a 1M token context window at standard pricing. For the most capable tier overall, Anthropic also offers Claude Fable 5 (claude-fable-5).

Is migrating just a one-line model-string change?

Often, but not always. The current models removed temperature, top_p, top_k, the fixed budget_tokens thinking budget, and assistant-turn prefills — each returns a 400 if left in. Replace budget_tokens with adaptive thinking plus output_config.effort, and replace prefills with structured outputs.

What happens if I call the retired model after June 15?

The API returns an error — there is no silent failover to a newer model. Audit for the string 20250514 in your codebase before the deadline.

April 16, 2026

Claude 4 Release Date & Deprecation: What’s Changing June 2026

Updated June 10, 2026

Update: the Claude 4 family has since been superseded at the top of the lineup. As of June 10, 2026, Anthropic’s current lineup is Claude Fable 5 (the new top tier above Opus, $10 input / $50 output per MTok), Opus 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5). Full details: the Claude Fable 5 Complete Guide.

Last refreshed: May 15, 2026

Model Accuracy Note — Updated May 2026

Current flagship: Claude Opus 4.7 (claude-opus-4-7). Current models: Opus 4.7 · Sonnet 4.6 · Haiku 4.5. Claude Opus 4.7 referenced in this article has been superseded. See current model tracker →

Claude AI · Fitted Claude

Anthropic hasn’t announced a specific “Claude 4” as a distinct release — the current model generation is the Claude 4.x series, with Claude Opus 4.7 and Claude Sonnet 4.6 as the current flagship models. If you’re searching for Claude 4, you’re likely looking for the current generation. Here’s exactly what’s live, what the naming means, and what to watch for next.

Current status (April 2026): The Claude 4.x model family is live. Claude Opus 4.7 (claude-opus-4-7) and Claude Sonnet 4.6 (claude-sonnet-4-6) are Anthropic’s current production models. These are the “Claude 4” generation.

The Current Claude 4.x Lineup

Model	API String	Status	Position
Claude Opus 4.7	claude-opus-4-7	✅ Live	Flagship / maximum capability
Claude Sonnet 4.6	claude-sonnet-4-6	✅ Live	Production default / balanced
Claude Haiku 4.5	claude-haiku-4-5-20251001	✅ Live	Speed / cost efficiency

Claude Model Naming: How It Works

Anthropic uses a generation.version naming convention. The “4” in Claude 4.6 denotes the fourth major model generation. The “.6” is a version within that generation — a meaningful update that improves on the generation’s base capabilities without being an entirely new architecture.

This is why there’s no single “Claude 4 release date” to point to — the Claude 4.x family has been rolling out incrementally, with different model tiers (Haiku 4.5, Sonnet 4.6, Opus 4.7) shipping at different points within the generation. The generation is live; you’re using it now if you’re on current Claude models.

Claude 4 vs Claude 3: What Changed

The jump from Claude 3.x to Claude 4.x brought improvements across reasoning, coding accuracy, instruction-following, and agentic capability. Claude 3.5 Sonnet — released in mid-2024 — was the model that first clearly demonstrated Claude could compete with and often exceed GPT-4o on most professional benchmarks. The 4.x series extended those gains.

The most notable improvements in the 4.x generation: stronger performance on multi-step reasoning, better coherence in long agentic sessions, and improved accuracy on coding tasks including the SWE-bench benchmark for real-world software engineering.

What Comes After Claude 4.x

Anthropic hasn’t announced a Claude 5 release date or feature set. Based on the pace of releases — major generations arriving every several months, point releases more frequently — the next major generation will likely arrive within the year. When it does, the pattern will hold: the new mid-tier model (Sonnet) will likely outperform the current top-tier (Opus) on most tasks, at a fraction of the cost.

For anticipation content on the next Sonnet release, see Claude Sonnet 5: What We Know. For the current model API strings and specs, see Claude API Model Strings — Complete Reference.

Frequently Asked Questions

When does Claude 4 come out?

Claude 4 is already out — the current model generation is Claude 4.x. Claude Opus 4.7 and Claude Sonnet 4.6 are live and in production as of April 2026. There’s no separate “Claude 4” launch pending; you’re on it.

What is Claude 4?

Claude 4 refers to Anthropic’s fourth major model generation — currently the Claude 4.x series including Opus 4.6, Sonnet 4.6, and Haiku 4.5. The generation brought improvements in reasoning, coding, instruction-following, and agentic performance over Claude 3.

Is Claude 4 better than Claude 3?

Yes, across most benchmarks and practical tasks. The Claude 4.x generation improves on Claude 3 in reasoning accuracy, coding performance, long-context coherence, and agentic capability. Claude 3.5 Sonnet — the bridge between generations — was the model that first demonstrated Claude could consistently outperform GPT-4o on professional tasks.

Need this set up for your team?
Talk to Will →

Current Model Status — May 8, 2026

There is no “Claude 4” as a standalone release. The current generation is the Claude 4.x series. The flagship model right now is Claude Opus 4.7 — released April 16, 2026.

Model	API String	Status
Claude Opus 4.7	claude-opus-4-7	✓ Current flagship
Claude Sonnet 4.6	claude-sonnet-4-6	✓ Current
Claude Haiku 4.5	claude-haiku-4-5-20251001	✓ Current
Claude Sonnet 4 / Opus 4	claude-*-4-20250514	⚠ Retiring June 15, 2026
Claude Haiku 3	claude-3-haiku-20240307	✗ Retired — returns error

Source: Anthropic API release notes · Updated May 8, 2026

Claude Reference Hub

Everything you need to use Claude — pricing, models, API setup, and release history.

💰 Claude Pricing — All Plans & API Rates
🔌 Claude API Model IDs & Strings
📡 Current Claude Model Version Tracker
⚙️ How to Install Claude Code
🔑 Anthropic Console & API Keys
📅 Claude 4 Release & Deprecation Guide
📜 Claude Release History: Every Model
📈 Anthropic IPO: Timeline & Valuation
🗂 View Full Claude Reference Hub →

April 12, 2026

Claude Haiku vs Sonnet vs Opus: The Complete Three-Model Comparison

Last refreshed: June 9, 2026

Model Accuracy Note — Updated June 9, 2026

Current flagship: Claude Opus 4.8 (claude-opus-4-8). Current models: Opus 4.8 · Sonnet 4.6 · Haiku 4.5. Claude Opus 4.8 (claude-opus-4-8) is the current flagship as of April 16, 2026. Where this article references Opus 4.6 or earlier models, those references are historical. See current model tracker →. See current model tracker →

Claude AI · Fitted Claude

Choosing between Claude’s three models comes down to one question: how hard is the task, and how much does cost matter? Haiku 4.5, Sonnet 4.6, and Opus 4.8 each occupy a distinct position — this is the complete three-way breakdown so you can route work correctly from the start.

The routing rule in one sentence: Haiku for volume and speed, Sonnet for almost everything else, Opus for the tasks where Sonnet isn’t quite enough.

Haiku vs Sonnet vs Opus: Full Comparison

Spec	Haiku	Sonnet	Opus
API string	claude-haiku-4-5-20251001	claude-sonnet-4-6	claude-opus-4-8
Input price (per M tokens)	~$1.00	~$3.00	~$5.00
Output price (per M tokens)	~$5.00	~$5.00	~$25.00
Context window	200K	1M	1M
Speed	⚡ Fastest	⚡ Fast	🐢 Slower
Reasoning depth	Good	Excellent	Maximum
Writing quality	Good	Excellent	Maximum
Cost vs Sonnet	~4× cheaper	—	~5× more expensive

Claude Haiku 4.5: The Volume Model

Haiku is optimized for tasks that are high in quantity but low in complexity — situations where you’re running the same operation hundreds or thousands of times and cost per call is a real constraint. Classification, extraction, summarization, metadata generation, routing logic, short-form responses, and real-time features where latency matters more than depth.

The output quality on constrained tasks is strong. Where Haiku shows its limits is on open-ended, nuanced work — multi-step reasoning, long-form writing where voice consistency matters, or problems with competing constraints. For those, Sonnet is the right call.

Claude Sonnet 4.6: The Default

Sonnet handles the vast majority of professional work at a quality level that’s indistinguishable from Opus for most tasks. Writing, analysis, research, coding, summarization, strategy — Sonnet does all of it well. It’s the model to start with and the one most people should use as their production default.

The gap between Sonnet and Opus shows on genuinely hard tasks: novel multi-step reasoning, edge cases in complex code, nuanced judgment in ambiguous situations, or extended agentic sessions where small quality differences compound. For everything else, Sonnet is the right choice and a fraction of the cost.

Claude Opus 4.8: The Specialist

Opus earns its premium on tasks where maximum capability is the only variable that matters and cost is secondary. Complex legal or technical analysis, research synthesis across conflicting sources, architectural decisions with long-term consequences, extended agentic sessions, and any task where you’ve tried Sonnet and felt the output was a notch below what the problem deserved.

The practical test: if Sonnet’s output on a task is good enough, use Sonnet. Only reach for Opus when you’ve genuinely hit Sonnet’s ceiling on a specific problem. Most professionals do this on a small fraction of their actual workload.

The Decision Framework

Use Haiku when: same operation at high volume, output is constrained/structured, cost and speed matter, real-time latency required.

Use Sonnet when: any standard professional task — writing, coding, analysis, research. This should be your default 90% of the time.

Use Opus when: the task is genuinely hard, involves novel reasoning, Sonnet’s output wasn’t quite right, or quality is the only variable that matters regardless of cost.

For full pricing details, see Anthropic API Pricing. For a Haiku deep-dive, see Claude Haiku 4.5: Pricing, Use Cases, and API String. For the Opus vs Sonnet head-to-head, see Claude Opus 4.8 vs Sonnet.

Frequently Asked Questions

What’s the difference between Claude Haiku 4.5, Sonnet, and Opus?

Haiku is fastest and cheapest — built for high-volume, constrained tasks. Sonnet is the balanced production default with excellent quality across most professional work. Opus is the most capable model for complex reasoning — about 5× more expensive than Sonnet on input tokens.

Which Claude model should I use?

Start with Sonnet for almost everything. Switch to Haiku when you’re running the same operation at high volume and cost matters. Switch to Opus when Sonnet’s output on a specific task isn’t quite at the level the problem requires.

Is Claude Haiku 4.5 good enough for most tasks?

For structured, constrained tasks — yes, Haiku is strong. For open-ended writing, complex reasoning, or work requiring nuanced judgment, Sonnet is the right step up. The cost savings from Haiku are meaningful at scale, making it the right choice when the task fits its strengths.

Need this set up for your team?
Talk to Will →

April 12, 2026

Claude Haiku: Pricing, API String, Use Cases, and When to Use It

Last refreshed: May 15, 2026

Claude AI · Fitted Claude

Claude Haiku 4.5 is Anthropic’s fastest and most cost-efficient model — the right choice when you need high-volume AI at low cost without sacrificing the quality that makes Claude worth using. It’s not a cut-down version of the flagship models. It’s a purpose-built model for the tasks where speed and cost matter more than maximum reasoning depth.

When to use Haiku: Any time you’re running the same operation across many inputs — classification, extraction, summarization, metadata generation, routing logic, short-form responses — and cost or speed is a meaningful constraint. Haiku handles these at a fraction of Sonnet’s price with output quality that’s more than sufficient.

Claude Haiku 4.5 Specs (April 2026)

Spec	Value
API model string	claude-haiku-4-5-20251001
Context window	200,000 tokens
Input pricing	~$1.00 per million tokens
Output pricing	~$5.00 per million tokens
Speed vs Sonnet	Faster — optimized for low latency
Batch API discount	~50% off (~$0.50 input / ~$2.50 output)

Claude Haiku 4.5 vs Sonnet vs Opus

Model	Input cost	Speed	Reasoning depth	Best for
Haiku	~$1.00/M	Fastest	Good	High-volume, latency-sensitive
Sonnet	~$3.00/M	Fast	Excellent	Production workloads, daily driver
Opus	~$5.00/M	Slower	Maximum	Complex reasoning, highest quality

What Claude Haiku 4.5 Is Best At

Haiku is optimized for tasks where the output is constrained and the logic is clear — not open-ended creative or strategic work where maximum capability pays off. The practical use cases where Haiku earns its position:

Classification and routing — is this a support ticket, a bug report, or a feature request? Tag it and route it. Haiku handles thousands of these per hour at minimal cost.
Extraction — pull the names, dates, dollar amounts, or addresses from a document. Structured output from unstructured text at scale.
Summarization — condense articles, emails, or documents to key points. Haiku’s summarization is strong enough for most production use cases.
SEO metadata — generate title tags, meta descriptions, alt text, and schema markup in bulk. This is where Haiku shines for content operations.
Short-form responses — FAQ answers, product descriptions, short explanations. Anything where the output is a few sentences or a structured short block.
Real-time features — chatbots, autocomplete, inline suggestions — anywhere latency affects user experience.

Claude Haiku 4.5 vs GPT-4o Mini

GPT-4o mini is OpenAI’s comparable low-cost model and is less expensive than Haiku per token. The cost trade-off is real — GPT-4o mini is cheaper. The quality trade-off depends on the task. For instruction-following on complex structured outputs, Haiku tends to be more reliable. For simple, high-volume tasks where the output format is forgiving, the cost difference may favor GPT-4o mini. For teams already building on Claude for quality reasons, Haiku is the natural choice for high-volume work within that stack.

Using Claude Haiku 4.5 in the API

import anthropic

client = anthropic.Anthropic()

message = client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=256,
    messages=[
        {"role": "user", "content": "Classify this support ticket: ..."}
    ]
)

print(message.content)

For a full model comparison, see Claude Models Explained: Haiku vs Sonnet vs Opus. For API pricing across all models, see Anthropic API Pricing.

Frequently Asked Questions

What is Claude Haiku 4.5?

Claude Haiku 4.5 is Anthropic’s fastest and most affordable model — approximately $1.00 per million input tokens. It’s purpose-built for high-volume, latency-sensitive tasks like classification, extraction, summarization, and short-form generation where cost efficiency matters more than maximum reasoning depth.

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs approximately $1.00 per million input tokens and $5.00 per million output tokens. The Batch API reduces these to approximately $0.40 input and $2.00 output — roughly half price for non-time-sensitive workloads.

When should I use Claude Haiku 4.5 instead of Sonnet?

Use Haiku when your task is well-defined with a constrained output, you’re running it at high volume, and cost or latency is a meaningful consideration. Use Sonnet when the task is complex, requires nuanced reasoning, or produces longer open-ended outputs where maximum quality matters.

What is the Claude Haiku 4.5 API model string?

The current Claude Haiku 4.5 model string is claude-haiku-4-5-20251001. Always verify the current string in Anthropic’s official model documentation before production deployment.

Need this set up for your team?
Talk to Will →

April 12, 2026

Claude 3.5 Sonnet: The Release That Changed Claude’s Trajectory

Last refreshed: May 15, 2026

Historical reference: This article covers Claude 3.5 Sonnet and the Claude 4.x generation timeline.
Current flagship as of May 2026: Claude Opus 4.7 (claude-opus-4-7).
See current models →

Claude AI · Fitted Claude

Claude 3.5 Sonnet was Anthropic’s mid-2024 flagship model — the release that significantly closed the gap between Claude and GPT-4o and established Claude as a serious competitor for daily professional use. Here’s what it was, how it compared at launch, and where it fits in the current model lineup.

Current status: Claude 3.5 Sonnet has been succeeded by Claude Sonnet 4.6 (claude-sonnet-4-6). If you’re building something new, use the current Sonnet model. If you’re maintaining a system built on Claude 3.5, check Anthropic’s deprecation schedule for transition timing.

Claude 3.5 Sonnet: What It Was

Claude 3.5 Sonnet launched in June 2024 and was Anthropic’s strongest model at the time — outperforming Claude 3 Opus on most benchmarks while being significantly faster and cheaper. This made it an unusual release: the mid-tier model in a new generation beating the top-tier model from the previous generation. It set the pattern for how Anthropic structures model generations.

At launch, Claude 3.5 Sonnet scored at the top of industry benchmarks on graduate-level reasoning, coding, and mathematics. It was the first Claude model to support computer use — the ability to see and interact with computer interfaces — in beta.

Model Generations: Where 3.5 Sonnet Fits

Model	Generation	Status
Claude 3 Opus / Sonnet / Haiku	Claude 3 (early 2024)	Deprecated / legacy
Claude 3.5 Sonnet / Haiku	Claude 3.5 (mid 2024)	Superseded
Claude Sonnet 4.6	Claude 4.x (current)	✅ Current production default
Claude Opus 4.7	Claude 4.x (current)	✅ Current flagship

Why Claude 3.5 Sonnet Was a Landmark Release

Before 3.5 Sonnet, the conventional wisdom was that Claude Opus 4.7 was the model you reached for on serious tasks, accepting higher cost and slower speed. Claude 3.5 Sonnet changed that calculus — it was fast enough to use as a daily driver and capable enough to replace Opus on most tasks. The cost savings were substantial for anyone running high-volume API workloads.

The release also marked Claude’s first serious push into coding benchmarks — it scored highly on SWE-bench, a test of real-world software engineering tasks, which attracted significant developer attention and migration from GPT-4o.

Claude 3.5 Sonnet vs. Current Models

The current Claude Sonnet 4.6 builds on what Claude 3.5 Sonnet established, with improvements across reasoning, coding, instruction-following, and context handling. If you were a Claude 3.5 Sonnet user, the upgrade path is straightforward — switch the model string and expect better performance across most tasks.

For current model strings and specs, see Claude API Model Strings — Complete Reference. For a comparison of current Sonnet vs. Opus, see Claude Opus 4.7 vs Sonnet: Which Model Should You Use?

Frequently Asked Questions

Is Claude 3.5 Sonnet still available?

Claude 3.5 Sonnet has been superseded by Claude Sonnet 4.6. Anthropic maintains older models for a period after new releases but eventually deprecates them. Check Anthropic’s model documentation for current availability and any deprecation notices for Claude 3.5 Sonnet API strings.

What was the Claude 3.5 Sonnet API model string?

The Claude 3.5 Sonnet model strings were claude-3-5-sonnet-20240620 and the later version claude-3-5-sonnet-20241022. If you have production systems using these strings, verify their current availability in Anthropic’s model documentation and plan migration to current model strings.

Should I upgrade from Claude 3.5 Sonnet to the current Sonnet?

Yes. Claude Sonnet 4.6 outperforms Claude 3.5 Sonnet across most tasks. Migration is typically straightforward — update the model string in your application and test your core use cases. The current model string is claude-sonnet-4-6.

Need this set up for your team?
Talk to Will →

April 12, 2026

Claude Sonnet 5: What We Know About the Next Claude Model (2026)

Updated June 10, 2026

There is still no “Claude Sonnet 5.” The current Sonnet remains Sonnet 4.6 — Anthropic’s newest release is instead Claude Fable 5, a new top tier above Opus. As of June 10, 2026, Anthropic’s current lineup is Claude Fable 5 (the new top tier above Opus, $10 input / $50 output per MTok), Opus 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5). Full details: the Claude Fable 5 Complete Guide.

Last refreshed: May 15, 2026

Model Accuracy Note — Updated May 2026

Claude AI · Fitted Claude

Anthropic hasn’t announced Claude Sonnet 5 yet — but based on how they’ve released models so far, here’s what we know about the Claude model roadmap, what Sonnet 5 is likely to look like when it arrives, and how to stay current as the lineup evolves.

Current status (April 2026): The current Sonnet release is Claude Sonnet 4.6 (claude-sonnet-4-6). Anthropic has not announced a release date or feature set for a Sonnet 5. This page tracks what we know and will be updated as Anthropic makes announcements.

The Current Claude Model Lineup

Model	API String	Status
Claude Opus 4.7	claude-opus-4-7	✅ Current flagship
Claude Sonnet 4.6	claude-sonnet-4-6	✅ Current production default
Claude Haiku 4.5	claude-haiku-4-5-20251001	✅ Current fast/cheap tier
Claude Sonnet 5	—	⏳ Not yet announced

How Anthropic Releases Models

Anthropic follows a consistent pattern: new models launch across the Haiku 4.5, Sonnet 4.6, and Opus 4.7 tiers, often in sequence rather than simultaneously. Sonnet tends to be the first tier developers get meaningful access to at each generation — it’s the workhorse tier, and Anthropic has historically prioritized making it available broadly.

Major model generations arrive roughly every several months. Point releases (like 4.5 → 4.6) happen more frequently and often bring targeted capability improvements rather than fundamental architecture changes. A “Sonnet 5” designation would signal a new major generation rather than an incremental update.

What to Expect From Claude Sonnet 5

Based on the pattern across Claude generations, each new major Sonnet release has delivered: improved reasoning and instruction-following, better code generation, expanded context handling, and lower cost relative to the previous generation’s Opus tier. The trajectory has consistently moved toward making the mid-tier model do what only the top-tier could do previously.

Specific feature claims about an unannounced model would be speculation. What’s documented is the direction: Anthropic is investing heavily in extended thinking, agentic capabilities, and multimodal performance. Those priorities will almost certainly shape what Sonnet 5 looks like when it ships.

How to Stay Current on Claude Model Releases

The most reliable sources for Claude model announcements:

Anthropic’s blog (anthropic.com/news) — official launch announcements
Anthropic’s model documentation (docs.anthropic.com/en/docs/about-claude/models) — current API strings and deprecation notices
Anthropic’s changelog — incremental updates and point releases
This page — updated as new Claude model information becomes available

Should You Wait for Sonnet 5?

For most use cases, no. Claude Sonnet 4.6 is a capable production model. If you’re building something today, build on the current model and upgrade when the new one releases — that’s the standard pattern for any production API dependency. Waiting for an unannounced model before starting development rarely makes sense.

If you’re doing initial architecture decisions and want to understand where the platform is heading, Anthropic’s research publications and roadmap hints from their public communications are worth tracking. But for day-to-day work, the current Sonnet is the right tool.

For the current model lineup with full specs, see Claude Models Explained: Haiku vs Sonnet vs Opus. For API model strings and how to use them, see Claude API Model Strings — Complete Reference.

Frequently Asked Questions

Has Anthropic announced Claude Sonnet 5?

No. As of April 2026, Anthropic has not announced Claude Sonnet 5 or provided a release date. The current Sonnet model is Claude Sonnet 4.6. This page will be updated when an announcement is made.

What is the current version of Claude Sonnet 4.6?

The current Claude Sonnet 4.6 version is Sonnet 4.6, with the API model string claude-sonnet-4-6. It’s the production default for most API workloads.

How often does Anthropic release new Claude models?

Anthropic releases major model generations every several months, with point releases more frequently. The pace has been accelerating — each year has brought multiple significant model updates across the Haiku 4.5, Sonnet 4.6, and Opus 4.7 tiers.

Need this set up for your team?
Talk to Will →

April 12, 2026