Claude Sonnet 5.5: Specs, Pricing, Limits and Availability Facts

Claude Sonnet 5.5 is a proprietary large language model from Anthropic, released on 28 September 2026 as the second model in the Claude 5.5 family. This profile collects the facts Anthropic publishes about it: API ID, context window, output limit, prices, platforms, benchmarks, system card findings, data handling and retirement date. It is written for developers, architects, buyers and governance teams who need checked figures rather than summaries. Every fact comes from Anthropic's own documentation, announcement or system card, cited in the sources list. Where Anthropic does not publish a figure, the page says so.

Last checked: 2026-11-15.

This is an independent reference page from NHI Mgmt Group based on public provider documentation; it is not sponsored or endorsed by any provider. It uses Anthropic's public documentation as of November 2026. Model details change, so confirm against Anthropic's current documentation.

Key takeaways

• Released 28 September 2026. Anthropic's release notes and announcement date the launch of claude-sonnet-5-5 to 28 September 2026, and the announcement describes it as the second model in the Claude 5.5 family.
• 1M tokens in, 128K tokens out. The models overview lists a 1M-token context window, 128K max output tokens, text and image input and text output, with a reliable knowledge cutoff of June 2026.
• $2 input and $10 output per million tokens. Standard API prices are $2 and $10 per MTok, cache hits have cost $0.10 since 7 October 2026 and the Batch API halves the rates.
• Thinking cannot be turned off. Sonnet 5.5 uses adaptive thinking with a default effort of high; the Models API reports thinking type disabled as unsupported, and between_tools is the documented way to skip up-front thinking.
• Active, retirement not sooner than 28 September 2027. The deprecations page lists the model as Active, and Anthropic gives at least 60 days' notice before retiring a publicly released model.

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is the Sonnet-line model of Anthropic's Claude 5.5 family. The models overview carries the tagline "The best combination of speed and intelligence" and rates its comparative latency as Fast. It succeeded Claude Sonnet 5 at the same input and output list prices, $2 and $10 per million tokens, with cache reads at half of Sonnet 5's $0.20. Anthropic's announcement describes it as "a clear upgrade over Claude Sonnet 5, runs 30%+ faster, and costs up to 30% less for most work".

The model ID claude-sonnet-5-5 follows the undated naming used for Claude 4.6 and later models. Anthropic's versioning page states that such an ID "is not an alias. It is the snapshot": the weights behind it do not change, and an updated version would ship under a new ID. Serving infrastructure such as routers and safety classifiers can still change. For how Anthropic and other providers name versions, see LLM Model Naming and Versioning Explained. For the whole Claude line-up, see Anthropic Models.

Key facts at a glance

As of 2026-11-15. Source: Anthropic models overview, pricing page, model deprecations page and release notes.

Release and version history

As of 2026-11-15. Source: Anthropic release notes. Entries are listed by date, oldest first.

The launch notes list five ways code written for Sonnet 5 can break. To skip up-front thinking, send thinking type between_tools at high effort or below instead of disabled. Forced tool use (tool_choice any and tool) returns a 400 error. Thinking blocks are tied to the model and conversation, and work only in the account that produced them or a linked account. On the Claude API and Google Cloud the earlier computer_20251124 tool is not accepted. The advisor tool rejects Opus 4.8, Opus 4.7 and Sonnet 5 as advisors.

How much does Claude Sonnet 5.5 cost?

As of 2026-11-15. Source: Anthropic pricing page. Prices in US dollars per million tokens (MTok).

Modifiers: setting inference_geo to "us" on the first-party API applies a 1.1x multiplier to all token categories. Regional and multi-region endpoints on Amazon Bedrock and Google Cloud carry a 10% premium over global endpoints for Claude 4.5 and later models. Claude Platform on AWS and Claude in Microsoft Foundry bill at the same per-model rates, converted to Claude Consumption Units at $0.01 per CCU.

Tool costs: the tool use system prompt adds 286 tokens for auto or none; the pricing page lists no figure for any or tool on Sonnet 5.5. Web search costs $10 per 1,000 searches plus tokens. Code execution is free when a 20260209 or later web search or web fetch tool is in the request; otherwise each organisation gets 1,550 free hours a month, then $0.05 per container hour.

Context window and output limits

The models overview recommends the Models API as the more reliable source for programmatic checks, since it returns live capabilities and max_input_tokens values; for this model it reports thinking.types.disabled.supported as false and thinking.types.between_tools.supported as true. A full 1M-token request costs $2 in input before caching.

Modalities and tools

• Input and output: text and image input, text output.
• Thinking: adaptive thinking controlled with the effort parameter (default high); between_tools skips up-front thinking at high effort or below.
• Tool use: forced tool use with tool_choice any or tool returns a 400 error.
• Computer use: computer_20251124 is not accepted on the Claude API and Google Cloud.
• Server tools: web search, web fetch and code execution are priced on the pricing page; bash and text editor tools add 325 and 974 input tokens respectively for Claude 4.7 and later.
• Advisor tool: rejects Opus 4.8, Opus 4.7 and Sonnet 5 as advisors.

For security controls around agentic tool use, see the Claude Agent SDK Security Guide and the Claude Code Security Guide.

Where is Claude Sonnet 5.5 available?

As of 2026-11-15. Source: release notes and announcement.

Partner platforms set their own retirement schedules, so dates on Vertex AI and Bedrock can differ from the Claude API. For enterprise controls in the Claude apps, see the Claude for Enterprise Security Guide.

Access restrictions

Claude Sonnet 5.5 is generally available: the release notes list no access request for the model. Usage is governed by the account's usage tier and rate limits. The system card describes safeguards that act on specific request types rather than on who can use the model:

• Cyber: a three-stage system (activation probe, lightweight classifier, trained LLM classifier); blocked requests fall back to Sonnet 5 on most interfaces. Vulnerability discovery in source code is permitted and discovery in compiled binaries is blocked.
• Chemical and biological: the same misuse classifiers as Opus 5, with no fallback model.
• Frontier AI development: narrow safeguards, with blocks falling back to Sonnet 5.
• Conventional weapons and distillation: blocking classifiers with no fallback.

The system card states that blocking safeguards are transparent and do not covertly alter responses.

Benchmarks (provider-reported, dated)

Provider-reported scores from Anthropic's announcement of 28 September 2026. Anthropic notes that Artificial Analysis ran GDPval-AA on a pre-release deployment with a since-fixed bug, so that score may understate performance. Only Anthropic models are shown. Independent leaderboard figures are not included because none were fetched for this page.

Benchmark scores depend on effort setting, tools and harness, so they are not directly comparable with figures produced under other conditions.

Model card and system card

Anthropic published "System Card: Claude Sonnet 5.5", dated 28 September 2026. For what these documents contain in general, see Model Cards and System Cards Explained. The card states:

• Framework: it cites Anthropic's Responsible Scaling Policy, the August 2026 Risk Report and a Frontier Compliance Framework covering California SB 53 and the EU AI Act General-Purpose AI Code of Practice.
• Training data: a proprietary mix of public internet information, public and private datasets, user feedback or permitted data, and synthetic data; the ClaudeBot crawler follows robots.txt. Reliable knowledge cutoff June 2026.
• Risk thresholds: treated as meeting CB-1 and Autonomy-1, not crossing CB-2 or Autonomy-2.
• Alignment: risk assessed as "low"; improves on or matches Sonnet 5 on most metrics, trails Opus 5.5 overall, and its reasoning is less legible than many previous models.
• Sections: RSP risk areas, cyber, safeguards and harmlessness, agentic safety including prompt injection, alignment, model welfare and capabilities.

See the Frontier AI Model Risk Frameworks Guide for how such reports are structured.

Data handling

• Zero data retention: the announcement states Sonnet 5.5 is available with ZDR. ZDR is enabled per organisation by Anthropic's sales team and covers eligible features on the Messages and Token Counting endpoints.
• Covered Models: Sonnet 5.5 is not on Anthropic's Covered Models list (Fable and Mythos models), which requires 30-day retention.
• Feature retention: Batch processing data is kept 29 days and code execution data up to 30 days; flagged content can be kept up to 2 years even under ZDR.
• Training use: the ZDR page states retained data is never used for model training without express permission.
• Data residency: inference_geo "us" keeps inference in the US at a 1.1x price multiplier.

For key handling around API access, see the Anthropic API Keys Security Guide.

Deprecation status

"Not sooner than" is the earliest possible date, not a fixed schedule. The deprecations page names claude-sonnet-5-5 as the recommended replacement for retired Sonnet models.

How Claude Sonnet 5.5 differs from other models in its family

As of 2026-11-15. Source: models overview and pricing page. Models listed by price, lowest first.

Within the Sonnet line, Sonnet 5.5 keeps Sonnet 5's input, output and cache write prices and lists a lower cache hit price ($0.10 against $0.20). Its tool use system prompt is 286 tokens for auto or none. Within the 5.5 family, Opus 5.5 lists higher prices and Moderate latency, and Haiku 5.5 lists lower prices and the Fastest rating. Release-by-release detail is on Claude Sonnet Versions Compared and Claude Opus vs Sonnet vs Haiku 5.5.

Practitioner checklist

• Pin claude-sonnet-5-5 explicitly and record the ID in your model inventory with its "not sooner than" retirement date.
• Replace thinking disabled with between_tools, remove forced tool_choice, and test for 400 errors before migrating from Sonnet 5.
• Update computer use integrations on the Claude API and Google Cloud away from computer_20251124.
• Check that thinking blocks are not passed between unlinked accounts; they are dropped silently and the request still succeeds.
• Set the effort parameter deliberately; FrontierCode results differ between max and xhigh effort.
• Model costs with caching, batch and the 1.1x inference_geo multiplier included, not just the $2 and $10 list prices.
• Confirm ZDR enablement per organisation and note which features you use are outside ZDR.
• Subscribe to deprecation notices and check partner cloud schedules separately.

Standards and references

• Anthropic: Models overview (accessed 2026-11-15)
• Anthropic: Pricing (accessed 2026-11-15)
• Anthropic: Claude Platform release notes (accessed 2026-11-15)
• Anthropic: Model deprecations (accessed 2026-11-15)
• Anthropic: System Card, Claude Sonnet 5.5 (accessed 2026-11-15)
• Anthropic: Claude Sonnet 5.5 announcement (accessed 2026-11-15)
• Anthropic: Zero data retention (accessed 2026-11-15)
• Anthropic: Model IDs and versioning (accessed 2026-11-15)

Related NHI Mgmt Group resources: Anthropic Models, Claude Opus 5.5, Reasoning Models Explained, Claude for Enterprise Security Guide.