Last updated: August 2026 • Reference Guide for Claude API Engineers & Technical Architects
Direct Answer: Anthropic governs Claude API throughput via five usage tiers based on historical prepaid spend. Rate limits scale from Tier 1 (50 RPM / 20k–50k TPM) at $5 deposit up to Tier 4 (4,000 RPM / 400k+ TPM) at $1,000+ deposit. Rate limit errors (HTTP 429) are mitigated by exponential backoff with jitter, prompt caching, and using the Batch API for non-realtime jobs.
1. Anthropic API Usage Tier Qualifications & Thresholds
Tiers climb with spend and reliability — confirm live console limits.
Your API account’s rate limits are determined automatically based on your cumulative payment deposit and account standing in the Anthropic Console:
Usage Tier
Deposit Requirement
Credit Expiration / Waiting Period
Primary Purpose
Tier 1
$5 initial deposit
Instant activation upon card verification
Prototyping, local CLI tools, script development
Tier 2
$40 cumulative spend + 7 days standing
Automatic upgrade upon threshold
Small internal team tools, staging environments
Tier 3
$200 cumulative spend + 7 days standing
Automatic upgrade upon threshold
Production web applications, customer-facing agents
2. Requests Per Minute (RPM) and Tokens Per Minute (TPM) by Model
RPM/TPM differ by model — shapes matter more than memorized tables.
Rate limits apply independently across model families. High-intelligence models (Opus) have tighter token concurrency caps than lightweight models (Haiku):
Model Name
Tier 1 (RPM / TPM)
Tier 2 (RPM / TPM)
Tier 3 (RPM / TPM)
Tier 4 (RPM / TPM)
Claude Haiku 4.5
50 RPM / 50,000 TPM
1,000 RPM / 100,000 TPM
2,000 RPM / 200,000 TPM
4,000 RPM / 400,000 TPM
Claude Sonnet 4.6
50 RPM / 40,000 TPM
1,000 RPM / 80,000 TPM
2,000 RPM / 160,000 TPM
4,000 RPM / 400,000 TPM
Claude Opus 4.8
50 RPM / 20,000 TPM
1,000 RPM / 40,000 TPM
2,000 RPM / 80,000 TPM
4,000 RPM / 200,000 TPM
3. Diagnosing and Handling HTTP 429 Rate Limit Errors
429 is a pause — backoff, then retry with smaller batches.
When your application exceeds either its Requests-Per-Minute or Tokens-Per-Minute cap, the Anthropic API responds with an HTTP 429 Too Many Requests error containing response headers detailing when capacity will reset:
retry-after: Number of seconds to wait before retrying.
anthropic-ratelimit-requests-remaining: Remaining requests available in the current 60-second window.
anthropic-ratelimit-tokens-remaining: Remaining token budget available in the current window.
anthropic-ratelimit-tokens-reset: ISO timestamp indicating when the token pool will fully refresh.
Production Rate Limit Mitigation Playbook
Exponential Backoff with Full Jitter: Never retry immediately in a tight loop. Implement an exponential backoff formula with randomized jitter to prevent thundering herd spikes on your backend.
Utilize Prompt Caching: Cached prefix tokens read from memory bypass standard token generation latency and dramatically streamline token processing windows. Read our full Claude AI Pricing and Token Rates Guide for complete caching cost structures.
Route Heavy Jobs to the Batch API: For bulk processing, offline report generation, and data extraction, use the Anthropic Messages Batch endpoint. Batch jobs run against separate capacity pools, avoiding live interactive rate caps while cutting token costs by 50%.
Frequently Asked Questions (FAQ)
How do I increase my Claude API rate limits?
Rate limits scale automatically as you deposit funds and maintain clean billing standing in the Anthropic Console. Adding $40 moves your account to Tier 2, $200 to Tier 3, and $1,000+ to Tier 4. Enterprise accounts requiring higher limits can submit custom quota requests directly in the console.
What happens when I hit an HTTP 429 on Claude?
An HTTP 429 indicates that your requests or tokens per minute have exceeded your current tier allocation. Check the ‘retry-after’ response header, pause execution, and retry using exponential backoff.
Do prompt cache tokens count against TPM limits?
Yes, tokens read from cache still count toward your organization’s Tokens Per Minute (TPM) limit for that model family, though they process at significantly higher speed and cost 90% less.
Last updated: August 2026 • Verified against current Anthropic API & Subscription Schedules
Direct Answer: Claude AI costs range from $0 (Free tier) and $20/month (Claude Pro) to $20–$100/seat/month (Claude Team). For developers and API workloads, tokens are priced per million: Claude Haiku 4.5 ($0.80 input / $4.00 output), Claude Sonnet 4.6 ($3.00 input / $15.00 output), and Claude Opus 4.8 ($15.00 input / $75.00 output), with prompt caching reducing read costs by up to 90%.
1. Claude Subscription Plans & Seat Pricing (2026)
Subscription plans and seats — stale-proof framing.
Anthropic offers four primary subscription tiers for individual knowledge workers, engineering teams, and enterprise deployments:
Plan Tier
Monthly Price
Token Allocation & Access
Best For
Claude Free
$0 / month
Standard daily usage limits on Sonnet; rate-limited during peak demand hours.
2. Anthropic API Token Pricing: Full 2026 Model Schedule
API token meter — ceilings without sticky dollar stickers.
API pricing is calculated per million tokens (MTok). In 2026, prompt caching and the Batch API offer massive cost reductions for high-throughput production pipelines:
Model Name
Input (Prompt) / MTok
Output (Completion) / MTok
Prompt Cache Write
Prompt Cache Read
Claude Haiku 4.5
$0.80
$4.00
$1.00 / MTok
$0.08 / MTok (90% off)
Claude Sonnet 4.6
$3.00
$15.00
$3.75 / MTok
$0.30 / MTok (90% off)
Claude Opus 4.8
$15.00
$75.00
$18.75 / MTok
$1.50 / MTok (90% off)
Key API Cost Optimization Levers
Prompt Caching (90% Discount on Reads): For repetitive system prompts, codebase indexes, or knowledge bases, cached prefix tokens cost only 10% of standard input rates after a 5-minute warm window.
Batch API (50% Flat Discount): Non-realtime asynchronous requests (e.g. overnight batch content generation, log parsing, or vector indexing) receive an automatic 50% discount on both input and output tokens with a 24-hour SLA.
3. Claude Team vs. Enterprise: Which Model Fits Your Organization?
Team vs Enterprise — which model fits.
When evaluating multi-seat deployments for your company, the dividing line between Team and Enterprise is governance and consumption predictability:
Choose Claude Team ($20–$100/seat): When you want predictable, capped monthly software expenses. Standard Team includes bundled token allocations, preventing runaway bills from junior team members or automated loops.
Choose Claude Enterprise: When your IT security policies mandate SAML 2.0 Single Sign-On (Okta, Microsoft Entra ID), SCIM automated user provisioning, SIEM compliance export APIs, or HIPAA Business Associate Agreements (BAAs).
4. How Tygart Media Integrates Claude for Business Operations
At Tygart Media, we architect headless AI operating systems that connect Claude Code, Model Context Protocol (MCP), and business data pipelines without manual chat interactions. Whether you need custom MCP connectors, automated editorial queues, or full Claude AI Team Implementations, our custom architectures turn conversational AI into durable business software.
Frequently Asked Questions (FAQ)
How much does Claude Pro cost per month?
Claude Pro costs $20 per month (plus applicable local taxes) or $200 per year when billed annually. It unlocks 5x the usage capacity of the free tier, access to Claude Opus and Sonnet, priority bandwidth during peak hours, and early access to new features.
What is the difference between Claude Team and Claude Pro?
Claude Pro is an individual single-user subscription ($20/mo). Claude Team is designed for 5 or more users ($20-$100/seat/mo), adding central administration, shared project workspaces, team billing, and higher per-seat usage allowances.
How does Anthropic prompt caching reduce API costs?
Prompt caching allows developers to store frequently used context (such as long system instructions, documentation, or codebases) in memory. Subsequent requests reading from the cache receive a 90% discount on input tokens ($0.30/MTok on Sonnet vs $3.00/MTok standard).
Are tokens included in Claude Enterprise seats?
Under the 2026 pricing model, Claude Enterprise seats start at approximately $20/user/month for identity and platform access, with actual token consumption billed separately at standard API rates based on team usage.
The Claude Agent SDK tutorial starts here — the SDK (formerly the Claude Code SDK, renamed late 2025) eliminates the boilerplate of building agentic loops by hand, shipping the same tool execution, context management, and permission system that powers Claude Code into a Python or TypeScript library you can embed in any product, pipeline, or internal tool.
This is a practical build guide. It covers when to use an agent versus a script, what the SDK actually does, how to set one up with working code, and what to watch for in production.
When to Use an Agent vs. a Script
Agent vs script — choose deliberately.
Use an agent when the number of steps to complete the task is unpredictable. If the workflow can be hardcoded, a linear script is faster, cheaper, and easier to debug.
This is Anthropic’s own guidance in Building Effective Agents, and it’s the right frame. The common mistake is reaching for agents because agents are fashionable — not because the problem requires them.
Agents fit:
Open-ended research tasks where the number of searches needed varies
Code debugging where the error chain isn’t known in advance
Multi-step data pipelines where decisions at each step depend on prior outputs
Any workflow where the model needs to try, observe, and adjust
Scripts fit:
Known sequences of steps that always run in the same order
Simple data transformation with no conditional branching
Any task where the output of each step is fully predictable
The cost implication matters too: a 15-step agentic research task can hit 200K+ tokens without optimization. Agents are expensive when you don’t need them.
How the Claude Agent SDK Works
How the Agent SDK loop behaves in practice.
The SDK automates the ReAct loop — Reason, Act, Observe, repeat — so you define the tools and instructions and the SDK handles the rest. You never write the prompt → check stop_reason → execute tool → loop boilerplate yourself.
The core loop the SDK manages:
Send the task to Claude with available tool definitions
Claude reasons and produces a tool call (or a final answer)
The SDK executes the tool in the local environment
The SDK sends the result back to Claude
Claude observes and decides: call another tool or produce final output
Loop until done
This continues until Claude produces a response with no tool calls. The SDK handles conversation history, token tracking, error handling, and session management across the entire loop.
A working agent requires three things: a task, tool definitions, and a Runner call. Everything else is configuration.
from claude_agent_sdk import ClaudeAgentOptions, Runner
import subprocess
import json
# Define tools the agent can use
tools = [
{
"name": "run_command",
"description": "Run a shell command and return its output",
"input_schema": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The shell command to execute"
}
},
"required": ["command"]
}
},
{
"name": "read_file",
"description": "Read the contents of a file",
"input_schema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "File path to read"
}
},
"required": ["path"]
}
}
]
# Tool execution handlers
def execute_tool(tool_name: str, tool_input: dict) -> str:
if tool_name == "run_command":
result = subprocess.run(
tool_input["command"],
shell=True,
capture_output=True,
text=True
)
return result.stdout or result.stderr
elif tool_name == "read_file":
with open(tool_input["path"], "r") as f:
return f.read()
return f"Unknown tool: {tool_name}"
# Configure and run the agent
options = ClaudeAgentOptions(
model="claude-sonnet-4-6",
max_turns=20, # safety ceiling
tools=tools,
tool_executor=execute_tool
)
result = Runner.run_sync(
task="Check the disk usage on this machine and report the top 5 largest directories under /home",
options=options
)
print(result.final_output)
That’s a complete working agent. The SDK handles the loop; the tool definitions and executor are the only custom code.
Adding Cost Controls
Add cost controls before multi-turn agents hit production.
Always set a max_turns ceiling and a token budget. An uncapped agent loop can run indefinitely on an ambiguous task.
options = ClaudeAgentOptions(
model="claude-sonnet-4-6",
max_turns=20,
max_tokens_per_turn=4000, # cap per individual turn
tools=tools,
tool_executor=execute_tool
)
Cost at 20 turns using Claude Sonnet 4.6 with an average of 2,000 tokens per turn:
Input: 40,000 tokens × $3/M = $0.12
Output: 10,000 tokens × $15/M = $0.15
Total per agent run: ~$0.27
At 1,000 agent runs per month: ~$270. At 10,000: ~$2,700. Budget from these numbers, not from seat prices.
Switching the inner loop to Haiku 4.5 for tool selection and Sonnet only for synthesis cuts cost significantly:
# Route lighter reasoning to Haiku, reserve Sonnet for synthesis
light_options = ClaudeAgentOptions(model="claude-haiku-4-5-20251001", ...)
heavy_options = ClaudeAgentOptions(model="claude-sonnet-4-6", ...)
Multi-Turn Agents (Conversational)
For agents where a human asks follow-up questions across multiple turns, maintain conversation history and pass it on each call.
from claude_agent_sdk import ClaudeAgentOptions, Runner
conversation_history = []
def chat_with_agent(user_message: str) -> str:
conversation_history.append({
"role": "user",
"content": user_message
})
options = ClaudeAgentOptions(
model="claude-sonnet-4-6",
max_turns=10,
tools=tools,
tool_executor=execute_tool,
messages=conversation_history # full history each call
)
result = Runner.run_sync(task=user_message, options=options)
conversation_history.append({
"role": "assistant",
"content": result.final_output
})
return result.final_output
# Usage
print(chat_with_agent("What Python packages are installed on this system?"))
print(chat_with_agent("Which of those are outdated?"))
Claude Managed Agents vs. the Agent SDK
The Agent SDK runs locally in your environment. Claude Managed Agents runs in Anthropic’s cloud infrastructure with persistent sessions, built-in tools, and cross-session memory. Choose based on where you need the agent to execute.
Agent SDK
Managed Agents
Where it runs
Your server / local machine
Anthropic-managed cloud
Persistent sessions
Manual (maintain history)
Built-in
Cross-session memory
Manual
Built-in (public beta)
Built-in tools
Bring your own
20+ included
Multi-agent coordination
Manual
Built-in
Cost
API tokens only
API tokens + platform fee
Control
Full
Managed
The Agent SDK is right for custom environments, data that can’t leave your infrastructure, and workflows deeply embedded in existing systems. Managed Agents is right when you want to skip infrastructure and get to the agent behavior faster.
What Goes Wrong in Production
The most common production failures are uncapped loops, conversation history that grows without bound, and tool definitions written too vaguely.
Uncapped loops: An agent on an ambiguous task will keep calling tools indefinitely without a max_turns ceiling. Always set one. Always check message.subtype rather than is_error — a max-turns termination doesn’t set is_error: true correctly in some SDK versions.
Growing conversation history: Each turn adds tokens to history. At 20 turns on a complex task, history can push 100K+ tokens. Summarize aggressively between phases for long-running agents: prompt Claude to summarize phase 1 outputs before starting phase 2.
Vague tool definitions: Tool descriptions are how Claude decides which tool to call and how to use it. Vague descriptions produce tool call errors and unnecessary retry loops. Write tool descriptions as precisely as you would write a function docstring — what it does, what inputs it expects, what it returns.
camelCase vs snake_case mismatch:AgentDefinition uses camelCase (disallowedTools); ClaudeAgentOptions uses snake_case (disallowed_tools). This caught teams in early SDK versions.
The Claude Agent SDK is Anthropic’s Python and TypeScript library for building autonomous AI agents. It wraps the same agentic loop that powers Claude Code — tool execution, context management, and session handling — so developers don’t build that infrastructure from scratch. It was formerly called the Claude Code SDK and was renamed in late 2025.
What is the difference between the Agent SDK and Claude Code?
Claude Code is Anthropic’s interactive terminal-based development tool for agentic coding. The Agent SDK is the programmatic library for embedding agent behavior in custom applications and pipelines. They share the same underlying agent loop and tool system. Claude Code stays in the picture for interactive development; the SDK is for production automation.
How much does it cost to run an agent?
Agent cost is API token cost only (no platform fee for the SDK itself). A 20-turn agent on Claude Sonnet 4.6 with 2,000 tokens average per turn costs approximately $0.27. At 10,000 agent runs per month, that’s about $2,700. Switching the tool selection loop to Haiku 4.5 and reserving Sonnet for synthesis significantly reduces cost.
When should I use Managed Agents instead of the Agent SDK?
Use Managed Agents when you want cloud-hosted execution, persistent cross-session memory, built-in tools (20+ included), and multi-agent coordination without building that infrastructure yourself. Use the Agent SDK when you need local execution, full control over the environment, or your data can’t leave your infrastructure.
Claude wins on coding quality and long-context reliability. GPT-5 wins on raw speed and cost per token. The right choice depends on which workload you’re optimizing for — and for most serious agentic coding workflows, Claude is the default for good reasons.
This comparison covers the metrics that matter for production API decisions in 2026: pricing at each tier, latency benchmarks, coding benchmark scores, context window handling, and where each model actually performs better. No marketing claims — just the numbers and where they point.
The Models Being Compared
Compare APIs by job shape — not by hype.
The relevant comparison in 2026 is Claude Sonnet 4.6 / Opus 4.8 against GPT-5 / GPT-5.5 — the mid-tier workhorses and frontier flagships from each lab.
Model
Provider
Input (per 1M tokens)
Output (per 1M tokens)
Context
Claude Haiku 4.5
Anthropic
$0.80
$4
1M tokens
Claude Sonnet 4.6
Anthropic
$3
$15
1M tokens
Claude Opus 4.8
Anthropic
$15
$75
1M tokens
GPT-5
OpenAI
$1.25
$10
400K tokens
GPT-5.5
OpenAI
$5
$30
1M tokens
The pricing gap is the first thing to understand: GPT-5 is cheaper per token than Claude Sonnet at every tier. Claude Opus is the most expensive flagship at any lab. That cost difference only makes sense if the quality difference justifies it — and for specific workloads, it does.
Coding Performance
Claude leads on coding benchmarks in 2026. Claude Sonnet scores approximately 77% on SWE-bench Verified versus roughly 72% for GPT-5. Claude Opus 4.8 and Fable 5 push higher still — Fable 5 is the current leader on AutomationBench.
SWE-bench Verified measures a model’s ability to solve real GitHub issues — fixing bugs, implementing features, navigating existing codebases. It’s the most production-relevant coding benchmark available.
Why Claude leads on coding:
Better multi-step refactor reliability on large codebases
Stronger instruction-following in complex, multi-constraint prompts
More consistent behavior across long agentic loops without drift
Claude Code and Cursor both default to Claude models — a market signal that carries weight
Where GPT-5 is competitive on coding:
Faster time-to-first-token for autocomplete-style workloads
GPT-5.5’s terminal-based coding benchmark (Terminal-Bench: 82.7%) is strong
Codex — OpenAI’s coding-specific deployment — is built on GPT-5.5 and optimized for that workload
The practical rule: for interactive coding assistance and agentic code execution, Claude Opus or Sonnet. For high-frequency autocomplete at scale where speed matters more than quality depth, GPT-5 mini or Haiku-class models.
Latency
GPT-5 is faster. OpenAI generally delivers 80–110 tokens per second on GPT-5; Claude Sonnet runs 60–90. Claude Haiku 4.5 is the fastest model in this comparison — first token in under 600ms on medium prompts, outpacing GPT-4.1 Mini by roughly 4x in March 2026 benchmarks.
Latency matters differently depending on the use case:
Use case
Which latency matters
Winner
Interactive chat / autocomplete
Time-to-first-token
GPT-5 (or Claude Haiku)
Agentic batch processing
Throughput, quality
Claude Sonnet / Opus
Long-context document analysis
Context handling
Claude (1M vs GPT-5’s 400K)
Real-time voice pipeline
TTFT + throughput
OpenAI Realtime API (no Claude equivalent)
For most production agentic workflows where the agent is running asynchronously, the latency difference between Claude Sonnet and GPT-5 is negligible compared to the quality difference on complex tasks.
Context Window
Context window and output limits are different ceilings.
Claude’s 1M token context window is a meaningful technical advantage over GPT-5’s 400K. At 1M tokens, entire medium-sized codebases, full legal contract libraries, or complete email archives fit in a single context without chunking or retrieval engineering.
GPT-5.5 also ships with a 1M context window, but at $5/$30 per million tokens compared to Claude Sonnet at $3/$15. For long-context workloads where you need the full window, Claude Sonnet is both more capable and cheaper than GPT-5.5.
Practical implications of the context gap at the mid-tier (Claude Sonnet vs GPT-5):
Codebases over 300K tokens: Claude handles them without chunking; GPT-5 requires retrieval engineering
Long contract or document review: Claude reads the full document in one pass
Multi-session agent context: Claude Managed Agents with memory handles this; GPT-5 requires custom solutions
Cost Comparison for Real Workloads
OpenAI is cheaper per token at every tier, but Claude’s 90% prompt caching discount and batch API 50% discount close the gap significantly for production workloads with repeated system prompts.
Workload cost comparison at scale:
Workload
Claude Sonnet
GPT-5
Notes
10K daily chat queries (~500 tokens avg)
~$15/day
~$6.25/day
GPT-5 cheaper
Same, with 80% prompt caching
~$4.50/day
—
No GPT-5 equivalent discount
100M tokens/month agentic batch
~$1,500
~$625
GPT-5 cheaper without caching
Same, with Claude batch API (50% off)
~$750
~$625
Near parity
The conclusion: for high-volume workloads with repeated context (system prompts, persistent agent instructions), Claude’s caching discounts make it competitive with GPT-5 on cost. For simple, stateless, high-frequency calls with no repeated context, GPT-5 is cheaper.
Tool Use and Agent Reliability
Claude is the dominant choice for agentic tool use in 2026. The Claude Agent SDK, Managed Agents platform, and Claude Code are purpose-built for autonomous multi-step workflows. OpenAI has function calling and a code interpreter, but no equivalent managed agent infrastructure.
Where this matters in practice:
Claude Code and Cursor lean on Claude because the model follows multi-step instructions with better consistency
Claude Managed Agents runs cloud-sandboxed agents with persistent memory, built-in tools, and multi-agent coordination — OpenAI has no direct equivalent
For complex tool-use chains where the agent needs to recover from errors and continue, Claude’s behavior is more reliable
Where OpenAI has an edge:
Computer Use is available natively on GPT-5 for web browsing and desktop control workflows
OpenAI’s Realtime API integrates speech-to-text, LLM, and text-to-speech in one pipeline — no Claude equivalent exists
Which API to Choose
Which API to choose depends on the workload class.
Use Claude for: coding, long-context document work, agentic workflows, and anything where instruction-following quality matters more than cost per token. Use GPT-5 for: high-frequency stateless calls, voice pipeline integration, and workloads where cost is the primary constraint.
Decision framework:
If your primary need is…
Choose
Agentic coding and multi-step execution
Claude Sonnet / Opus
Long-context document analysis (>400K tokens)
Claude Sonnet
High-volume, cheap inference at scale
GPT-5 / Claude Haiku
Voice + LLM pipeline
OpenAI Realtime API
Production agent with persistent memory
Claude Managed Agents
Terminal-based coding workload
GPT-5.5 / Codex
The most common real-world answer: Claude Sonnet for the reasoning-heavy core, Claude Haiku or GPT-5 for high-frequency auxiliary calls where speed and cost dominate. Running both APIs is normal and often optimal.
Yes, on most production coding benchmarks. Claude Sonnet scores approximately 77% on SWE-bench Verified versus about 72% for GPT-5. Claude also handles multi-step refactoring and large codebase navigation more reliably. GPT-5.5 on Terminal-Bench (82.7%) is competitive for terminal-based workflows, and OpenAI’s Codex is optimized for that use case.
Is Claude more expensive than GPT-5?
Per token, yes — Claude Sonnet is $3/$15 per million tokens versus GPT-5 at $1.25/$10. Claude’s prompt caching (up to 90% off cached input) and batch API (50% off) close the gap significantly for production workloads with repeated context. Opus is the most expensive flagship model available.
Does Claude have a larger context window than GPT-5?
Yes at the mid-tier. Claude Sonnet has a 1M token context window; GPT-5 has 400K. GPT-5.5 also offers 1M tokens but at a higher price than Claude Sonnet. For workloads requiring full-document context without chunking, Claude Sonnet is the better mid-tier choice.
Which API is faster?
GPT-5 is faster on raw throughput (80–110 tokens/second vs Claude Sonnet’s 60–90). Claude Haiku 4.5 is the fastest model in this comparison for time-to-first-token. For most asynchronous agentic workloads, latency differences are less significant than quality differences.
Claude Managed Agents is the product. Slack, Notion, Jira, and Asana are just the interface. Anthropic is building the invisible execution layer that powers the next generation of enterprise software.
There is a pattern emerging in enterprise AI that most people are reading wrong. They see Anthropic launch Claude Tag in Slack and think “chatbot upgrade.” They see Claude show up inside Notion and think “productivity feature.” They see AI agents appear in Jira and Asana and think “automation plugin.”
They are missing the architecture underneath all of it.
Anthropic is not building a better chatbot. It is building the invisible agent runtime that sits beneath every collaboration tool your team already uses. The company’s Claude Managed Agents (CMA) platform — launched in public beta on April 8, 2026 — is the infrastructure layer that makes this possible. And the speed at which partners are embedding it tells you everything about where enterprise software is heading.
What Claude Managed Agents Actually Is
What Claude Managed Agents actually is — the runtime layer.
Claude Managed Agents is a set of composable APIs for building and deploying production AI agents on Anthropic’s cloud infrastructure. The service handles sandboxed code execution, session persistence, credential management, scoped permissions, and end-to-end tracing — all the operational complexity that previously kept agents stuck in proof-of-concept limbo.
The architecture rests on three primitives: the Agent (configuration and behavior), the Environment (sandboxed execution), and the Session (the event log that tracks everything the agent does). What makes this interesting architecturally is how Anthropic decoupled the “brain” from the “hands.” Claude’s reasoning runs on Anthropic’s own infrastructure while the code execution sandbox spins up independently — and in parallel. The brain starts reasoning immediately while the sandbox provisions, delivering roughly 60% faster time-to-first-token at the p50 level and over 90% faster at p95, according to Anthropic’s engineering team.
Pricing follows a transparent model: standard Claude API token rates plus $0.08 per session-hour of active runtime during the current beta period. Runtime is measured to the millisecond and only accrues while the agent is actively executing — idle time waiting for input or tool confirmations does not count.
For teams that need to keep execution inside their own perimeter, CMA supports self-hosted sandboxes through partners including Cloudflare, Daytona, Modal, and Vercel, or custom VPC deployments. MCP tunnels allow agents to connect to private Model Context Protocol servers inside your network without exposing them to the public internet. A Vaults system keeps credentials out of the sandbox entirely using envelope encryption. And a feature called Dreaming runs scheduled reviews of past sessions to curate agent memory — essentially letting agents learn from their own operational history.
The Embedded Layer: Where CMA Actually Lives
Embedded layer: where CMA actually lives in the stack.
The real story is not the infrastructure. It is where that infrastructure shows up. In the ten weeks since CMA launched, Anthropic has embedded its agent runtime inside the collaboration tools that enterprises already depend on. This is not a roadmap — these integrations are live or in active beta.
Slack: Claude Tag as Persistent Team Member
Claude Tag, launched June 23, 2026, replaces Anthropic’s original Claude in Slack integration with something fundamentally different. This is not a chatbot you summon with a slash command. It is a persistent AI team member that lives in your channels, builds memory across conversations, and can take initiative through what Anthropic calls “ambient mode” — proactively surfacing information, following up on forgotten threads, and keeping teams updated across the organization.
Claude Tag is multiplayer by design: one Claude identity per channel, accessible to everyone, with the ability to hand off half-finished tasks between team members. It runs on Claude Opus 4.8, Anthropic’s most capable model released May 28, 2026. And internally, Anthropic reports that Claude Tag is already approving and incorporating 65% of the code changes their product team submits. The existing Claude in Slack app will be retired on August 3, 2026. Claude Tag is available on Enterprise and Team plans.
Notion: Claude as External Agent
On May 13, 2026, Notion launched its Developer Platform version 3.5, which introduced the External Agents API. This API lets AI agents — including Claude — operate inside your Notion workspace as first-class participants. They can read pages, write to databases, create tasks, trigger automations, and be @-mentioned directly in documents. Claude operating through this API can chain actions together: read a project brief, check the task database for related work, draft a new document, and create a linked task entry — all in a single session, running on CMA infrastructure with full sandboxing.
Asana: AI Teammates
Asana built AI Teammates on CMA — agents that pick up assigned tasks inside projects, draft deliverables, and hand back outputs for human review. Specialist agents handle specific workflows: the Campaign Brief Writer turns scattered notes into structured briefs, the Workflow Optimizer identifies process gaps and builds automations, and the Compliance Specialist checks work against regulatory standards. Asana’s CTO said CMA let them ship these features “dramatically faster” than any prior approach to agent development.
Atlassian: Claude Agent for Jira
Atlassian released Claude Agent for Jira, built on CMA infrastructure, which lets teams assign work items directly to Claude from the Jira UI. The agent clones the repository, analyzes the codebase, implements changes on an independent branch, pushes the code, and opens a draft pull request — streaming real-time status updates back to the Jira work item throughout the process.
Sentry: From Bug Detection to Merge-Ready PR
Sentry’s existing AI debugging agent, Seer, already used Claude for root cause analysis. With CMA, Sentry extended the workflow from diagnosis to automated fixing — the agent takes Seer’s root cause output, generates a fix, opens a branch with the changes, and creates a pull request for developer review. Sentry processes over one million root cause analyses per year and provides near-immediate reviews on over 600,000 pull requests per month. The CMA integration was built by a single engineer in weeks, eliminating months of custom agent runtime development.
Rakuten: Specialist Agents Across the Enterprise
Rakuten deployed specialist agents across product, sales, marketing, and finance using CMA, with each agent deployed in approximately one week. Agents plug into Slack and Teams, letting employees assign tasks and receive deliverables including spreadsheets, slides, and applications. In the pilot, Rakuten reported a 97% drop in critical first-pass errors, with cost down more than 30% and latency reduced by 34%, without any loss in output quality.
KPMG: Global Professional Services Alliance
On May 19, 2026, KPMG and Anthropic announced a global alliance and launched “Digital Gateway Powered by Claude.” The partnership embeds Claude, Cowork, and CMA directly into KPMG’s client delivery platform, with an initial focus on tax and private equity clients. Building an AI agent for tax regulation workflows previously took weeks and required switching between multiple tools. With CMA integrated into Digital Gateway, KPMG says the same capability takes minutes. The alliance extends to KPMG’s 276,000-person global workforce.
The Strategic Pattern: Agent Runtime as a Service
Step back from the individual integrations and the strategic pattern becomes clear. Anthropic is not trying to own the interface. It is deliberately positioning CMA as the execution layer underneath interfaces that other companies own. Slack owns the messaging UI. Notion owns the workspace UI. Jira owns the project tracking UI. Anthropic owns the agent brain that powers all of them.
This is a fundamentally different strategy from its two largest competitors.
OpenAI chose vertical integration. When OpenAI launched Workspace Agents on April 22, 2026, it positioned ChatGPT itself as the central hub — a no-code successor to custom GPTs that connects to Slack, Salesforce, Google Drive, and Notion through plugins. Agents are created inside ChatGPT, accessed from ChatGPT, and managed through ChatGPT. OpenAI wants to own the surface area.
Google chose platform depth. At Google Cloud Next on April 22, 2026, Google unveiled the Gemini Enterprise Agent Platform — a reimagined evolution of Vertex AI — alongside Workspace Intelligence, a semantic unifying layer that connects data across Docs, Slides, Gmail, and the broader Google Cloud ecosystem. Google’s agent platform supports 200+ models including Claude, and the Agent2Agent (A2A) protocol enables distributed peer-to-peer agent communication. Google is leveraging its data moat and distribution at the platform level.
Anthropic chose tool-centric orchestration. Rather than owning the UI (OpenAI) or the platform (Google), Anthropic is embedding its agent runtime into every tool through composable APIs and the Model Context Protocol. The platform you use becomes irrelevant — whether it is Slack, Notion, Jira, Asana, or Sentry — because the agent brain running underneath is Claude on CMA.
This is the agent-as-a-service model. And it may be the most defensible position of the three, because it does not require users to change their behavior or migrate to a new platform. The agent shows up where they already work.
What the Numbers Say About Enterprise Agent Adoption
The macro context supports Anthropic’s timing. Gartner predicts that 40% of enterprise applications will include embedded task-specific agents by the end of 2026, up from less than 5% in 2025. McKinsey’s April 2026 analysis found that agentic AI can enable automation of 60 to 80 percent of routine infrastructure work over time, translating to a 20 to 40 percent run-rate cost reduction in initial deployments.
The gap between experimentation and production remains the defining challenge. Industry research compiled from major firms shows that nearly four in five enterprises have experimented with or deployed agents in some form, but fewer than one in nine are running them in production at a scale that generates measurable business value. For the agents that do reach production, the average return on investment is 171% — though 19% of deployments never reach payback at all.
That production gap is exactly what CMA is designed to close. The infrastructure burden — sandboxing, session persistence, credential isolation, error recovery, observability — is the bottleneck. Engineering teams routinely dedicated significant senior engineering resources for months before a single agent reached production. CMA eliminates that layer entirely, which is why partners like Asana, Sentry, and Rakuten report shipping production agents in days or weeks rather than quarters.
What This Means for Businesses Already Using These Tools
If your organization uses Slack, Notion, Jira, or Asana — and statistically, you use at least two of them — you are about to encounter Claude whether you planned to adopt it or not. This is not a technology decision your IT team is making. It is a feature that your existing vendors are shipping.
The practical implications are significant. Claude Tag in Slack means your team channels will have an AI participant that remembers past conversations, can be handed tasks asynchronously, and may proactively surface information. Claude in Notion means your project documentation, databases, and task boards can be read, analyzed, and acted upon by an agent that chains actions together. Claude Agent for Jira means development tickets can be assigned to an AI that clones your repo, writes code, and opens pull requests.
For agencies and service providers managing client work across multiple tools, the embedded agent layer changes the economics fundamentally. Work that previously required a human to context-switch between Slack, Notion, and a project management tool — reading a brief here, updating a task there, drafting a document somewhere else — can be handled by an agent that operates across all of them simultaneously. The coordination tax that consumes a substantial share of knowledge work time is the exact problem embedded agents are built to solve.
The companies that benefit most will be the ones that have clean operational systems — structured task boards, documented processes, well-organized project databases — because agents can only act on information they can read. Messy Notion workspaces and disorganized Jira boards will limit what agents can accomplish. Operational hygiene just became a competitive advantage.
What This Means for Solo Operators Already Running Agent Infrastructure
There is a specific audience that should be paying very close attention to CMA: the solo operators and small agency owners who have already built their own agent stacks from scratch. If you are running scheduled Claude tasks on a GCP Compute Engine VM, connecting to WordPress via REST API proxies, piping work orders through Notion, monitoring Gmail for client replies, and publishing content through MCP-connected pipelines — you have already built a version of what CMA is productizing.
The economics question is worth doing the math on. A lightweight GCP VM running 24/7 to host recurring agent tasks — news desk monitors, outreach reply checks, newsletter extraction, scheduled content audits — costs a fixed monthly rate whether the agents are actively working or sitting idle. CMA at $0.08 per session-hour of active runtime only charges when agents are executing. For tasks that run for a few minutes every few hours, the per-session billing model could be substantially cheaper than keeping a VM warm around the clock. A task that runs for ten minutes six times a day would cost roughly $0.08 per day on CMA, versus the cost of a VM instance that never sleeps.
But the migration path is not ready yet, and solo operators should understand exactly where the gaps are before making any infrastructure decisions.
The biggest gap is MCP tunnels. CMA’s ability to connect agents to private MCP servers inside your network is still in research preview — not production-ready. If your agent stack depends on a private WordPress REST API proxy, a Notion workspace connected via MCP, or any internal tool that is not exposed to the public internet, CMA cannot reach it today. The Vaults system for credential management is promising, but it does not solve the network connectivity problem for self-hosted infrastructure.
The second gap is orchestration control. Solo operators who have built their own agent infrastructure typically have precise control over scheduling, retry logic, error handling, and the exact sequence of tool calls. CMA’s Dreaming feature — which reviews past sessions to curate agent memory — is an interesting approach to agent learning, but it is not the same as having direct control over a cron job that fires at 6:00 AM, checks three data sources in a specific order, and writes results to a specific Notion database with a specific schema.
The thesis for solo operators is straightforward: CMA is almost certainly the future migration path for self-hosted agent infrastructure. The economics favor it for intermittent workloads, the managed security and sandboxing eliminate operational risk you are currently carrying yourself, and the session persistence model solves problems that custom agent runtimes handle poorly. But the plumbing — particularly MCP tunnels to private infrastructure — is not production-ready. Track it closely. Do not migrate yet. When MCP tunnels graduate from research preview to general availability, revisit the math and the connectivity story. That is the trigger point.
The Risk Nobody Is Talking About
The risk nobody talks about — agents that act with memory.
There is a tension in this model that deserves attention. When Claude operates as an invisible layer inside tools you already trust, the boundary between the tool’s native capabilities and the AI agent’s actions blurs. A Jira ticket that was “completed” might have been implemented by Claude, reviewed by a human for thirty seconds, and merged. A Notion project plan that looks thorough might have been generated by an agent that filled in the sections with plausible-sounding content.
The embedded model works precisely because it reduces friction — but reduced friction also means reduced scrutiny. Organizations adopting embedded agents need to build review processes that match the speed at which agents can produce output. The 171% average ROI from agent deployments accounts for the value created, but it does not account for the subtle quality risks of production work generated by systems that are confident, fluent, and occasionally wrong.
Anthropic has built guardrails into CMA — sandboxed execution, credential isolation, session logging — but the governance layer for reviewing agent output at enterprise scale is still largely unsolved. This is a space where internal operational discipline matters more than the technology itself.
Where This Goes Next
Claude Tag launched on Slack first. Anthropic has indicated plans for wider rollout beyond Slack. If the pattern holds, expect Claude Tag’s persistent team member model to appear in Microsoft Teams, Discord, and any other collaboration surface where teams coordinate work.
The CMA primitives are designed to be composable, which means the partner integration list will grow rapidly. Any SaaS company with an API and a workflow that involves reading context, making decisions, and taking actions is a candidate for CMA integration. Customer support platforms, CRM systems, design tools, analytics dashboards, HR systems — the addressable surface is essentially every tool that knowledge workers touch.
Gartner’s long-term projection estimates that agentic AI could drive approximately 30% of enterprise application software revenue by 2035, surpassing $450 billion. If Anthropic’s embedded strategy succeeds, a meaningful slice of that revenue flows through CMA as the underlying runtime — regardless of whose logo is on the interface.
The chatbot era is ending. The embedded agent era is starting. And Anthropic is betting that the company that owns the invisible execution layer wins the market, even if no end user ever sees its name.
Claude Managed Agents is a set of composable APIs launched by Anthropic on April 8, 2026 in public beta. CMA lets developers build and deploy production AI agents on Anthropic’s cloud infrastructure, handling sandboxed code execution, session persistence, credential management, and end-to-end tracing. The architecture separates the “brain” (Claude reasoning) from the “hands” (code execution sandbox), enabling parallel processing and faster agent responses.
How much do Claude Managed Agents cost?
During the current public beta, CMA pricing is standard Claude API token rates plus $0.08 per session-hour of active runtime. Runtime is measured to the millisecond and only accrues while the agent is actively executing — idle time does not count. GA pricing has not been finalized and may differ from the beta rate.
What is Claude Tag in Slack?
Claude Tag is Anthropic’s persistent AI team member for Slack, launched June 23, 2026. Unlike a traditional chatbot, Claude Tag lives in channels, builds memory across conversations, takes initiative through ambient mode, and works asynchronously. It is multiplayer — one Claude identity per channel that all team members interact with. Claude Tag runs on Claude Opus 4.8 and is available on Enterprise and Team plans. It replaces the original Claude in Slack app, which retires August 3, 2026.
Which tools have Claude Managed Agents embedded?
As of June 2026, CMA is embedded in Slack (via Claude Tag), Notion (via the External Agents API), Asana (AI Teammates), Atlassian Jira (Claude Agent for Jira), and Sentry (extending the Seer debugging agent). Enterprise deployments include Rakuten (specialist agents across product, sales, marketing, and finance) and KPMG (Digital Gateway Powered by Claude for tax and private equity clients).
How does Anthropic’s agent strategy differ from OpenAI and Google?
Anthropic uses a tool-centric orchestration approach, embedding its agent runtime inside existing tools via composable APIs and the Model Context Protocol (MCP). OpenAI chose vertical integration with Workspace Agents, positioning ChatGPT as the central hub. Google chose platform depth with the Gemini Enterprise Agent Platform and Workspace Intelligence semantic layer. Anthropic’s approach does not require users to change platforms — the agent shows up where they already work.
What percentage of enterprise apps will have embedded AI agents by end of 2026?
Gartner predicts that 40% of enterprise applications will include embedded task-specific agents by the end of 2026, up from less than 5% in 2025. However, fewer than one in nine enterprises currently run agents in production at scale, suggesting significant growth ahead.
Can Claude Managed Agents run inside a private network?
Yes. CMA supports self-hosted sandboxes through partners including Cloudflare, Daytona, Modal, and Vercel, or custom VPC deployments. MCP tunnels allow agents to connect to private Model Context Protocol servers inside your network without public exposure. A Vaults system keeps credentials out of the sandbox using envelope encryption.
Direct Answer (August 2026): Claude Fable 5 is positioned as Anthropic’s advanced research & multi-agent architecture model. On API endpoints, Fable 5 is priced at $10.00/MTok input ($1.00 cached read) and $50.00/MTok output, available for specialized agentic reasoning workloads.
Claude Fable 5 (claude-fable-5) is Anthropic’s most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. On the Claude API it is priced at $10 per million input tokens and $50 per million output tokens — double the rate of Claude Opus 4.8 — with a 1M-token context window and up to 128K output tokens per request. It reached general availability on June 9, 2026. The verified pricing and access details are below.
Pricing at a glance
Fable 5 pricing at a glance — stale-proof framing.
All figures below are from Anthropic’s official pricing and models pages. Prices are in USD per million tokens (MTok). Fable 5 includes the full 1M-token context window at standard pricing — there is no long-context premium.
Item
Claude Fable 5
Model ID (API)
claude-fable-5
Base input
$10 / MTok
Output
$50 / MTok
5-minute cache write
$12.50 / MTok
1-hour cache write
$20 / MTok
Cache hit / read
$1 / MTok
Batch API input / output
$5 / MTok · $25 / MTok
Context window
1M tokens
Max output
128K tokens
How Fable 5 compares to Opus, Sonnet, and Haiku
How Fable 5 compares to Opus, Sonnet, and Haiku.
Fable 5 sits at the top of Anthropic’s lineup, a tier above the Opus models. The per-token cost difference is the clearest way to see where it fits.
Model
Input $/MTok
Output $/MTok
Context
Max output
Claude Fable 5
$10
$50
1M
128K
Claude Opus 4.8
$5
$25
1M
128K
Claude Sonnet 4.6
$3
$15
1M
64K
Claude Haiku 4.5
$1
$5
200K
64K
Where you can use Fable 5
Where you can use Fable 5.
At general availability, Fable 5 is offered across Anthropic’s first-party API and all major cloud platforms, plus claude.ai subscription plans (subject to the access note below). The model IDs differ by platform.
Surface
Availability / model ID
Claude API (first-party)
Generally available — claude-fable-5
Claude Platform on AWS
Generally available — claude-fable-5
Amazon Bedrock
Generally available — anthropic.claude-fable-5
Google Vertex AI
Generally available — claude-fable-5
Microsoft Foundry
Generally available
claude.ai — Pro, Max, Team, Enterprise
Promotional access June 9–22, 2026 (see below)
claude.ai — Free plan
Not included
Consumer-plan access and the promotional window
For claude.ai subscribers, Anthropic launched Fable 5 with a time-limited promotion rather than a permanent plan inclusion. From June 9 through June 22, 2026, Fable 5 was included on the Pro, Max, Team, and seat-based Enterprise plans at no extra charge. During that window, Anthropic’s documentation states that Fable 5 usage “counts toward your plan’s usage limits, and you won’t be charged anything extra,” but that it draws from those limits “at a higher rate than other models.” The Free plan was explicitly excluded.
Anthropic’s announced plan was that after June 22, 2026, Fable 5 would no longer be included in plan usage limits, and continued use on claude.ai would require usage credits — a pay-as-you-go balance for usage beyond what a plan includes.
Integration notes that affect cost and handling
Fable 5 differs from the Opus, Sonnet, and Haiku models in a few ways that matter when you wire it into an application. It ships with safety classifiers that can decline a request: when that happens, the Messages API returns stop_reason: "refusal" as a successful HTTP 200 response, not an error. You are not billed for a request that is refused before any output is generated, and Anthropic provides server-side, client-side, and manual fallback paths to retry on another Claude model. Adaptive thinking is always on (thinking: {"type": "disabled"} is not supported), and the raw chain of thought is never returned — thinking.display controls whether thinking blocks contain a summary or are empty. Fable 5 also uses the tokenizer introduced with Opus 4.7, which can produce roughly 30–35% more tokens for the same text than older models, so re-baseline your token counts rather than assuming parity with earlier Claude models.
How much does Claude Fable 5 cost?
On the Claude API, Fable 5 costs $10 per million input tokens and $50 per million output tokens. Prompt-cache writes are $12.50/MTok (5-minute) or $20/MTok (1-hour), cache reads are $1/MTok, and the Batch API halves the rate to $5/MTok input and $25/MTok output.
Is Fable 5 more expensive than Claude Opus 4.8?
Yes. Fable 5 is priced at exactly double Opus 4.8 on both input ($10 vs $5 per MTok) and output ($50 vs $25 per MTok). Both share a 1M-token context window and 128K max output.
Which claude.ai plans include Fable 5?
From June 9 to June 22, 2026, Fable 5 was included on the Pro, Max, Team, and seat-based Enterprise plans at no extra cost, drawing from plan usage limits at a higher rate. The Free plan was not included. Anthropic’s plan was to move continued claude.ai use to usage credits after June 22.
What is the difference between Fable 5 and Mythos 5?
They share the same specs ($10/$50 per MTok, 1M context, 128K output) and June 9, 2026 launch date. Fable 5 is the generally available model with built-in safety classifiers that can decline requests; Mythos 5 is offered only in limited availability.
💼 Deploying Claude or AI Infrastructure in Your Business?
The Message Batches API lets you submit up to 100,000 Claude requests in a single call and receive results asynchronously — at exactly 50% of standard token prices. Most batches finish in under an hour. Results remain downloadable for 29 days. This page covers every verified limit, the per-tier rate limit tables, and how batch pricing stacks with prompt caching.
Pricing: 50% off standard rates
Batch pricing — half-rate framing without sticky dollars.
Every token processed through the Message Batches API is billed at half the standard input and output price. No quality difference from synchronous requests — only timing. The table below shows verified batch prices for active models.
A batch expires if processing has not completed within 24 hours. Any individual request within that batch that did not finish is marked expired — you are not billed for expired or errored requests. Batch results (the JSONL file) are accessible for download for 29 days after the batch was created; after that the batch object itself is still visible but results can no longer be downloaded.
Message Batches API rate limits by tier
The Message Batches API has its own rate-limit pool, shared across all models, separate from the standard Messages API limits. The “processing queue” count refers to individual batch requests (not batches) that have been submitted but not yet completed by the model.
RPM here limits how fast you can make HTTP requests to the Batches API endpoints (create, retrieve, list, cancel). It does not limit how many individual requests inside a batch are processed per minute — that is governed by the queue cap above. If high demand causes processing to slow, more individual requests within a batch may reach the 24-hour expiration limit.
Stacking batch pricing with prompt caching
The Batches API documentation explicitly states that the 50% batch discount and prompt caching discounts stack. Cache writes incur a one-time cost at 1.25x the base input rate (5-minute TTL) or 2x (1-hour TTL); subsequent cache reads cost 0.1x the base input rate. Because batches process asynchronously and may take longer than 5 minutes, Anthropic recommends using the 1-hour cache duration for batch requests that share large context.
The following example uses Claude Opus 4.8 (standard input: $5.00/MTok) to show what each token type costs in a batch with a 1-hour cached system prompt.
Token type
Multiplier applied
Effective price per MTok
How calculated
Uncached input (standard)
1x
$5.00
Baseline
Uncached input (batch)
0.5x
$2.50
50% batch discount
Cache write — 1h TTL (batch)
2x × 0.5x = 1x
$5.00
2x write cost, then 50% batch
Cache read (batch)
0.1x × 0.5x = 0.05x
$0.25
10% read cost, then 50% batch
Output (batch)
0.5x of $25.00
$12.50
50% batch discount on output
In practice: if you cache a 50,000-token system prompt once and then read it across 1,000 batch requests, the cache write costs $0.25 (50K tokens at $5.00/MTok effective), while 1,000 cache reads cost $12.50 total (50M tokens at $0.25/MTok). The same 50 million tokens without caching would cost $125 in batch input (50 MTok at the $2.50/MTok batch rate). Cache hit rates on batches vary; Anthropic’s documentation notes typical rates of 30% to 98% depending on traffic patterns, since batch requests are processed concurrently rather than sequentially.
How results come back
How results come back from Message Batches.
When the batch finishes (or the 24-hour limit is reached), a results_url property is set on the batch object. Results are in JSONL format — one JSON object per line, in any order (not necessarily matching submission order). Each result carries the custom_id you assigned, plus a result object of type succeeded, errored, canceled, or expired. Streaming the results file rather than downloading it all at once is recommended for large batches. You are not billed for errored, canceled, or expired requests.
Does the Batches API count against my standard Messages API rate limits?
No. The Message Batches API has its own rate-limit pool that is tracked separately from the standard Messages API RPM, ITPM, and OTPM limits. You can use both simultaneously up to their respective limits.
What happens if my batch does not finish within 24 hours?
Any individual requests within the batch that did not complete are marked expired. You are not billed for those requests. The batch itself moves to ended status and whatever results did complete are available at the results_url.
Can I use extended thinking, tool use, or vision in a batch?
Yes. The Batches API supports vision, tool use (including server tools such as web search and code execution), system messages, multi-turn conversations, and extended thinking. The parameters not supported are stream: true, fast mode (speed), Threads parameters, and max_tokens: 0.
How long are batch results available for download?
Results are available for 29 days after the batch was created. After that window, the batch object remains visible in the Console and via the API, but the results file can no longer be downloaded.
Is the Batches API eligible for Zero Data Retention?
No. The Message Batches API is explicitly excluded from Zero Data Retention (ZDR). Data is retained under the feature’s standard retention policy regardless of your organization’s ZDR settings.
A million Claude tokens equals roughly 750,000 words on Claude Sonnet 4.6 — but only about 555,000 words on Claude Opus 4.7, Claude Opus 4.8, and Claude Fable 5. The gap comes from a new tokenizer that Anthropic introduced with Opus 4.7: it emits up to 35% more tokens from the same text. The only reliable way to measure your actual token count is the /v1/messages/count_tokens endpoint.
Token-to-word conversion by model (1 million tokens)
Token-to-word conversion framing.
Anthropic publishes word equivalents directly in the context-window tooltips on the official models overview page. The figures below come from those tooltips.
Model
Tokenizer
Context window
~Words per 1M tokens
~Pages per 1M tokens*
Claude Fable 5 (claude-fable-5)
New (Opus 4.7)
1M tokens
~555,000
~2,200
Claude Opus 4.8 (claude-opus-4-8)
New (Opus 4.7)
1M tokens
~555,000
~2,200
Claude Opus 4.7 (claude-opus-4-7)
New (Opus 4.7)
1M tokens
~555,000
~2,200
Claude Sonnet 4.6 (claude-sonnet-4-6)
Older
1M tokens
~750,000
~3,000
Claude Haiku 4.5 (claude-haiku-4-5)
Older
200k tokens
~150,000 (200K context)
~600 (200K context)
Claude Opus 4.6 (claude-opus-4-6)
Older
1M tokens
~750,000
~3,000
* Pages estimated at ~250 words per double-spaced page. These are approximations for typical English prose; actual counts vary by content type.
What the new tokenizer changed — and why it matters
What the new tokenizer changed — and why it matters.
Anthropic introduced a new tokenizer with Claude Opus 4.7. The official migration guide states that the new tokenizer “may use roughly 1x to 1.35x as many tokens when processing text compared to previous models (up to ~35% more, varying by content).” The most commonly cited figure across Anthropic’s documentation is roughly 30% more tokens for the same text.
The practical effect: a document that costs 1,000,000 tokens on Opus 4.6 or Sonnet 4.6 costs approximately 1,300,000 tokens on Opus 4.7, Opus 4.8, or Fable 5. Budgets built for the old tokenizer need to be re-baselined against the new one.
Tokenizer
Models
Approximate token increase vs. older tokenizer
New (introduced Opus 4.7)
Opus 4.7, Opus 4.8, Fable 5, Mythos 5
~30% typical; up to ~35% depending on content
Older
Opus 4.6, Sonnet 4.6, Haiku 4.5, Opus 4.5, Sonnet 4.5
Baseline
The token counting page also notes the comparison directly: “Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7, which produces roughly 30% more tokens than models before Claude Opus 4.7 for the same text.”
Use count_tokens — not tiktoken or ratio math
Use count_tokens — not tiktoken or ratio math.
Anthropic’s migration guide explicitly flags the risk: “Any code path that estimates tokens client-side or assumes a fixed token-to-character ratio should be re-tested against Claude Opus 4.7.” OpenAI’s tiktoken library is trained on a different vocabulary and produces different counts. It will not give accurate results for any Claude model.
The correct approach is the /v1/messages/count_tokens endpoint, passing the specific model you intend to use:
The endpoint returns a model-specific count. If you are migrating a workload from Sonnet 4.6 to Opus 4.8, count the same prompt with both model IDs and compare the two input_tokens values. The token counting endpoint is free to use (rate limits apply by usage tier). Anthropic notes that the returned count is an estimate; the actual count at inference time may differ by a small amount.
Quick reference: common document sizes
Document type
Approx. words
Tokens (older tokenizer)
Tokens (new tokenizer)
Novel (~400 pages)
~100,000
~133,000
~173,000
Long research paper
~20,000
~27,000
~35,000
Full context, Sonnet 4.6 (1M tokens)
~750,000
1,000,000
N/A (different model)
Full context, Opus 4.8 (1M tokens)
~555,000
N/A (different model)
1,000,000
These word estimates assume typical English prose. Code, structured data, and non-Latin scripts tokenize differently from natural language prose. Highly repetitive text and dense symbol-heavy content (like JSON or code) can fall well outside the ~0.75 words-per-token ratio.
Does the new tokenizer change what fits in the context window?
Yes, in one direction. The context window is still 1M tokens, but that window holds fewer words on the new tokenizer (~555k words) than on the old one (~750k words). A document that previously fit comfortably may now require trimming or chunking when moving to Opus 4.7, Opus 4.8, or Fable 5.
Does Sonnet 4.6 use the new tokenizer?
No. Claude Sonnet 4.6 uses the older tokenizer. Anthropic’s model overview page lists Sonnet 4.6’s 1M-token context window as equivalent to ~750k words, the same ratio as Opus 4.6 — confirming it has not adopted the Opus 4.7 tokenizer. Only Opus 4.7, Opus 4.8, Fable 5, and Mythos 5 use the new tokenizer.
Can I use tiktoken or another open-source tokenizer for Claude?
No. tiktoken is built for OpenAI models and uses a different vocabulary. It will not produce accurate token counts for any Claude model, and its error will be larger on the new Opus 4.7 tokenizer than on older Claude models. Use /v1/messages/count_tokens with the specific Claude model ID you plan to deploy.
Does the new tokenizer affect pricing?
Yes. Billing reflects token counts under the model’s tokenizer. If you migrate a workload from Opus 4.6 to Opus 4.8 and the new tokenizer produces 30% more tokens, your input token costs increase by roughly 30% before accounting for any per-token price difference between the models. Re-baseline cost estimates using the count_tokens endpoint rather than scaling from old measurements.
How many pages is the full 1M-token context window?
On models with the older tokenizer (Sonnet 4.6, Opus 4.6), 1 million tokens is approximately 3,000 double-spaced pages of typical English prose. On models with the new tokenizer (Opus 4.8, Fable 5), the same 1 million tokens holds approximately 2,200 pages. These are prose estimates — a 1M-token window filled with source code or dense structured data will span a very different page count.
Anthropic ships four distinct ways to put Claude to work as an agent, and they are easy to confuse. The short version: Claude Cowork and Claude Code are interactive products billed through your Claude subscription — Cowork for knowledge work in the desktop app, Code for software work in your terminal, IDE, desktop, or browser. The Claude Agent SDK and Managed Agents are programmatic surfaces for developers, billed through the API: the Agent SDK is a Python/TypeScript library that runs the agent loop inside your own process, while Managed Agents is a REST API where Anthropic runs the loop and hosts the sandbox. The tables below give the verified, side-by-side breakdown.
The decision matrix
Cowork vs Code vs Agent SDK vs Managed Agents matrix.
Each row is one surface. Read across for who it serves, whether you drive it turn-by-turn or hand it a goal, where the work executes, and how it is paid for.
Surface
Who it is for
Interactive vs autonomous
Where it runs
How it is billed
Claude Cowork
Knowledge workers (non-developers) — research, documents, file and spreadsheet work
Interactive, supervised — shows you the plan and waits for your approval before acting
The Claude desktop app on your own computer (macOS or Windows); not available on web or mobile
Claude subscription (Pro, Max, Team, Enterprise) — draws from your plan’s usage allocation
Interactive — you drive it in a session, though it can run agentically across files and tools
Your machine (terminal, VS Code, JetBrains, desktop app) or the browser at claude.ai/code
Claude subscription or an Anthropic Console (API) account
Claude Agent SDK
Developers building custom agents programmatically (Python or TypeScript)
Autonomous — Claude reads files, runs commands, and edits code on its own via the agent loop
Your own process and infrastructure
API key (pay-as-you-go credits); see the subscription note below for the June 15, 2026 change
Managed Agents
Developers running production or long-running agents without operating their own sandbox/session infrastructure
Autonomous — you send events, Claude executes tools and streams back results
Anthropic-managed cloud sandbox per session (or a self-hosted sandbox on your own infrastructure)
Claude API key + the managed-agents-2026-04-01 beta header (no subscription path)
Where billing actually differs
The cleanest way to split these four is by the wallet they draw from. The two interactive products are funded by a subscription; the two programmatic surfaces are funded by the API. This is the single distinction that trips people up most often, so it is worth stating plainly in its own table.
Surface
Billing model
Notes
Claude Cowork
Subscription
Included on Pro, Max, Team, and Enterprise. Multi-step tasks consume more of your usage allocation than chatting.
Claude Code
Subscription or API
Most surfaces require a Claude subscription or a Console account; the terminal CLI and VS Code also support third-party providers.
Claude Agent SDK
API (pay-as-you-go)
Authenticated with an ANTHROPIC_API_KEY; also supports Bedrock, Claude Platform on AWS, Vertex AI, and Azure. Anthropic does not permit claude.ai login for third-party agents built on the SDK.
Managed Agents
API (credits)
Requires a Claude API key and the beta header; enabled by default for API accounts.
One dated nuance is worth pinning down because it changes how subscription users pay for programmatic work. Starting June 15, 2026, Claude Agent SDK and claude -p usage on subscription plans no longer counts toward your Claude plan’s interactive usage limits; instead, eligible subscribers receive a separate monthly Agent SDK credit (per-user, not pooled), while subscription usage limits stay reserved for interactive use of Claude Code, Cowork, and Claude. If you use the Agent SDK with an API key from the Claude Platform, nothing changes — pay-as-you-go billing continues and you do not receive an Agent SDK monthly credit.
SDK vs Managed Agents: the programmatic split
SDK vs Managed Agents — the programmatic split.
Both programmatic surfaces let Claude run tools autonomously, but they differ in where the loop and the work live. Anthropic’s own comparison frames it this way: the Agent SDK “is a library that runs the agent loop inside your own process,” while Managed Agents “is a hosted REST API: Anthropic runs the agent and the sandbox, and your application sends events and streams back results.” Pick by who you want operating the infrastructure.
Dimension
Agent SDK
Managed Agents
Runs in
Your process, your infrastructure
Anthropic-managed infrastructure
Interface
Python or TypeScript library
REST API
Agent works on
Files on your infrastructure
A managed sandbox per session
Session state
JSONL on your filesystem
Anthropic-hosted event log
Best for
Local prototyping; agents that work directly on your filesystem and services
Production agents without operating sandbox/session infrastructure; long-running, asynchronous sessions
A common path, per Anthropic’s docs, is to prototype with the Agent SDK locally, then move to Managed Agents for production.
Quick chooser
Quick chooser for the right surface.
If you are not writing code and want Claude to finish a task on your computer, use Cowork. If you are a developer working interactively on a codebase, use Claude Code. If you are building your own agent and want it to run in your own process, use the Agent SDK. If you want Anthropic to run the agent and host the sandbox for long-running or production work, use Managed Agents.
Is Claude Cowork the same as Claude Code?
No. Both appear in the Claude desktop app, but Cowork is aimed at knowledge work (research, documents, spreadsheets, file management) for non-developers, while Claude Code is an agentic coding tool. Cowork runs only in the desktop app (macOS or Windows); Claude Code also runs in the terminal, VS Code, JetBrains, and the browser.
Does a Claude subscription cover the Agent SDK or Managed Agents?
Cowork and Claude Code are included with Claude subscriptions (Pro, Max, Team, Enterprise). The Agent SDK and Managed Agents are API surfaces authenticated with a Claude API key. As of June 15, 2026, subscription users do get a separate monthly Agent SDK credit for SDK and claude -p usage, but Managed Agents has no subscription path — it requires an API key and a beta header.
Where does the work actually execute for each surface?
Cowork runs on your own computer in the desktop app. Claude Code runs on your machine (or in the browser). The Agent SDK runs in your own process and infrastructure. Managed Agents executes in an Anthropic-managed cloud sandbox per session, or a self-hosted sandbox you control.
Is the Agent SDK built on Claude Code?
Yes. Per Anthropic, the Agent SDK “gives you the same tools, agent loop, and context management that power Claude Code, programmable in Python and TypeScript.” Anthropic also describes it as “Claude Code as a library.”
Is Managed Agents generally available?
No. As of June 13, 2026, Claude Managed Agents is in beta. Every Managed Agents endpoint requires the managed-agents-2026-04-01 beta header (the SDK sets it automatically), and access is enabled by default for API accounts.
Anthropic publishes a defined compliance posture for Claude: it holds SOC 2 Type I and Type II, ISO 27001:2022, and ISO/IEC 42001:2023 credentials; it will sign a Business Associate Agreement (BAA) covering HIPAA-ready services such as the first-party API and Enterprise plans; by default it does not train models on data sent under its commercial terms; and it offers a zero-data-retention (ZDR) arrangement on the Messages and Token Counting APIs. The hard part for buyers is the per-surface boundary — what the BAA covers, which features are blocked under ZDR or HIPAA, how long data is kept, and where it can be processed. Every figure below is drawn from Anthropic’s own trust, privacy, and developer documentation, with sources at the bottom. Eligibility, feature lists, and durations change; treat your signed contract and the live Trust Center as the controlling sources.
Certifications and attestations
Certifications and attestations overview.
Anthropic’s help center lists the following compliance credentials for its commercial products (Claude for Work and the Anthropic API). It directs customers to the Trust Portal at trust.anthropic.com to request copies of the underlying reports and certificates.
Credential
Status as described by Anthropic
Scope
SOC 2 Type I & Type II
Listed as held
Commercial products (Claude for Work, Anthropic API)
ISO 27001:2022
Certified
Information Security Management
ISO/IEC 42001:2023
Certified (issued by Schellman Compliance, LLC, accredited by the ANSI National Accreditation Board)
AI Management Systems
HIPAA
“HIPAA-ready configuration (BAA available)”
See BAA section
Anthropic describes itself as “one of the first frontier AI labs” to achieve ISO/IEC 42001:2023 certification, in an announcement dated January 13, 2025. The help-center certifications list does not mention ISO 27017, ISO 27018, FedRAMP, or CSA STAR; those are left out here rather than asserted. GDPR and CCPA are handled through Anthropic’s privacy program and customer agreements rather than as line-item “certifications” (see GDPR section).
HIPAA and the BAA: covered by product surface
HIPAA and the BAA by product surface.
Anthropic states it “provides a Business Associate Agreement (BAA) covering our HIPAA-ready services, such as use of our first-party API or Enterprise plans.” HIPAA readiness is enforced at the organization level: Anthropic provisions a dedicated HIPAA-enabled organization that automatically blocks non-eligible features. To process protected health information (PHI) on the API, an administrator must sign the BAA and contact sales to enable it; for Enterprise, an admin activates HIPAA compliance in the Claude Enterprise admin settings under “Data & Privacy” and signs the BAA there.
Surface
BAA / HIPAA-ready coverage
First-party Claude API (Messages API)
Covered as an Eligible Service (admin signs BAA, then contact sales)
Claude Enterprise
Covered once an admin activates HIPAA compliance and signs the BAA
Workbench and Console
Not covered
Claude Free, Pro, Max, Team
Not covered
Cowork
Not covered
Claude Code
Not covered under HIPAA readiness
Amazon Bedrock / Vertex AI
Not covered (cloud provider is the data processor; see those platforms)
Claude Platform on AWS / Microsoft Foundry
HIPAA readiness not available
Beta features (e.g., Claude in Office, Claude Design)
Generally not covered unless explicitly listed as eligible
Within the API, only a subset of features is HIPAA-eligible. Anthropic enforces this in code: a HIPAA-enabled organization that sends a non-eligible feature gets a 400 invalid_request_error naming the blocked feature. Anthropic states your signed BAA is the official source of truth for what is covered.
API feature
HIPAA-eligible
Messages API (/v1/messages)
Yes
Token counting
Yes
Web search
Yes (dynamic filtering not eligible)
Prompt caching, structured outputs, extended/adaptive thinking, citations, 1M context, PDF (inline), data residency, effort, fast mode, bash & text-editor tools, memory tool
PHI must appear only in message content, attached files, or related file names/metadata — never in JSON schema definitions (property names, enum/const values, or pattern regexes), because compiled schemas are cached separately and do not receive the same PHI protections. Anthropic notes workspace names, user contact details, billing data, and support tickets are not expected to contain PHI under the BAA.
Data retention (commercial default)
Under Anthropic’s commercial data retention policy, conversation content is not retained by default for the API, and API inputs and outputs are automatically deleted on the backend within 30 days of receipt or generation. For interface products such as Claude for Work, data persists until you delete it, after which it is removed from backend storage within 30 days. Two exceptions extend retention regardless of arrangement.
Data type / event
Retention
API inputs and outputs (default)
Auto-deleted within 30 days
Deleted conversation content (Claude for Work)
Removed from backend within 30 days
Inputs/outputs for a chat flagged as a Usage Policy violation
Data tied to feedback you submit (thumbs up/down, bug report)
5 years
Zero data retention (ZDR)
Zero data retention (ZDR).
With a ZDR arrangement, customer data is not stored at rest after the API response is returned, except where needed to comply with law or combat misuse. ZDR is requested through Anthropic sales and enabled per organization — it does not carry over automatically to new organizations under the same account. Even under ZDR, Anthropic retains User Safety classifier results, and may retain inputs and outputs for up to 2 years if a chat or session is flagged for a Usage Policy violation. CORS is not supported for ZDR organizations, so browser apps must call through a backend proxy.
Surface
ZDR coverage
Claude Messages API & Token Counting API
Eligible
Claude Code (Commercial org API keys, or via Claude Enterprise with ZDR enabled)
Eligible
Console and Workbench
Not eligible
Claude Teams & Claude Enterprise interfaces
Not eligible (except Claude Code via Enterprise with ZDR on)
Claude Free, Pro, Max
Not eligible
Claude Managed Agents
Not eligible (stateful; delete transcripts manually)
A handful of ZDR-eligible features are marked “Yes (qualified)” — structured outputs and cache diagnostics — meaning Anthropic retains a narrow, documented set of technical data (for example, a cached JSON schema for up to 24 hours since last use) rather than your prompts or Claude’s outputs.
Model-training policy and Covered Models
Anthropic’s Privacy Policy states it does not apply to content processed on behalf of business customers; that data is governed by the customer agreement. For the API specifically, Anthropic states retained data is never used for model training without your express permission. Anthropic’s consumer-terms update confirms the data-use changes “do not apply to services under our Commercial Terms,” including Claude for Work, Claude for Government, Claude for Education, and API use (including via Amazon Bedrock and Google Cloud’s Vertex AI). Training on commercial data happens only if a customer explicitly opts in (for example, the Development Partner Program).
One model-specific exception affects retention, not training: Claude Fable 5 and Claude Mythos 5 are designated Covered Models and require 30-day data retention. ZDR is not available for these two models; a request to either from an organization whose retention configuration doesn’t meet the requirement returns a 400 invalid_request_error. Organizations with ZDR can turn on 30-day retention for a single workspace (Console > Settings > Workspaces > Privacy controls) to use those models there while keeping ZDR elsewhere. On Bedrock, Vertex AI, and Microsoft Foundry, retention requirements for these models are set by each platform.
GDPR, data residency, and international transfers
For users in the EEA, UK, or Switzerland, the data controller is Anthropic Ireland, Limited; elsewhere it is Anthropic PBC. Where the EU or UK GDPR applies, Anthropic responds to verifiable data-subject requests within one calendar month. For transfers to countries without an adequacy decision, Anthropic relies on standard contractual clauses, and publishes its subprocessors at anthropic.com/subprocessors.
On data residency, the Claude API exposes two independent controls. inference_geo sets where inference runs per request — values are "global" (default) or "us" — and is supported on Claude Opus 4.6, Sonnet 4.6, and later (older models return a 400). Workspace geo controls where data is stored at rest and where endpoint processing happens; it is set at workspace creation and cannot be changed afterward. Per Anthropic’s documentation, "us" is currently the only available workspace geo, and only "us" and "global" inference geos are available — so there is currently no EU-resident storage option at the workspace level. US-only inference is priced at 1.1x the standard rate on supported models. Data residency is available on the Claude API (first-party) and Claude Platform on AWS; on Bedrock and Vertex AI the region is set by the endpoint or inference profile.
Does Anthropic train its models on my API or commercial data?
No, not by default. Anthropic’s Privacy Policy excludes business-customer content (governed by your customer agreement), and for the API it states retained data is never used for training without your express permission. The consumer data-use changes explicitly do not apply to Commercial Terms services. Training on commercial data requires an explicit opt-in.
Will Anthropic sign a BAA, and for what?
Yes. Anthropic signs a BAA covering HIPAA-ready services such as the first-party API and Enterprise plans. The Messages API is covered as an Eligible Service. It does not cover Workbench/Console, Free/Pro/Max/Team, Cowork, Claude Code, or beta features unless explicitly listed. An admin must sign the BAA and enable HIPAA readiness; the organization then auto-blocks non-eligible features.
What’s the difference between ZDR and HIPAA readiness?
Per Anthropic, ZDR prevents customer data from being stored at rest after the API response. HIPAA readiness is a broader set of safeguards (encryption, access controls, audit logging) that protect PHI throughout its lifecycle and lets data be retained with safeguards rather than deleted immediately. Anthropic states you do not also need ZDR if you have HIPAA readiness.
How long does Anthropic keep my data?
By default, API inputs and outputs are auto-deleted within 30 days. If a chat is flagged as a Usage Policy violation, inputs/outputs may be retained up to 2 years and trust & safety classification scores up to 7 years. Data tied to feedback you submit is kept 5 years. ZDR removes the default at-rest storage but does not remove the law/misuse exceptions.
Can I keep Claude inference and data in the EU?
Not at rest currently. The API’s inference_geo can pin inference to "us" or run "global", but Anthropic’s documentation lists "us" as the only available workspace geo (storage region). EU/UK data-subject rights and standard contractual clauses apply regardless, but an EU storage-residency option is not currently offered at the workspace level per the docs verified here.
