Skip to content
Model Change Index
  • OverviewNext shutdowns and latest changes
  • ShutdownsEvery date, one row per platform
  • ChangesReleases, deprecations, redirects and prices
  • LeaderboardEvery model, its scores and price
  • Check my stackYour models on one timeline
Track my stack

Claude Sonnet 5.5

ActiveAnthropicanthropic/claude-sonnet-5-55 platforms

No shutdown before this date. Claude Sonnet 5.5 stays on the Claude API until at least Sep 28, 2027.

≥ 11 mo
Earliest retirement
≥ 349 daysSep 28, 2027 · Claude API
Arena Text
1,476#19 of 128 · Arena
GPQA Diamond
95.6%#3 of 108 · Epoch AI
List price · $ per 1M
$2.00 in $10.00 outClaude API · cached input $0.10
Context window
1MMax output 128K tokens

Dates on every platform

5 listings · a floor is the earliest possible date
Claude Sonnet 5.5 on each platform: model ID, status, dates, replacement and source
PlatformModel ID and statusDeprecatedShuts downReplacement
Claude APIAnthropic: Model deprecations (opens in a new tab) · checked Oct 14, 2026claude-sonnet-5-5Active–Not sooner than–
Azure AI FoundryMicrosoft: Claude models in Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026claude-sonnet-5-5:1Active–None set–
Azure AI FoundryMicrosoft: Claude models in Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026claude-sonnet-5-5:2Active–None set–
Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026anthropic.claude-sonnet-5-5Active · also au.anthropic.claude-sonnet-5-5, eu.anthropic.claude-sonnet-5-5, global.anthropic.claude-sonnet-5-5, us.anthropic.claude-sonnet-5-5–Not sooner than–
Google Vertex AIGoogle Cloud: Claude Sonnet 5.5 on Google Cloud (opens in a new tab) · checked Oct 14, 2026claude-sonnet-5-5Active–Not sooner than–

Version 1 runs on Anthropic infrastructure.

Version 2 runs on Azure infrastructure.

In us-east-1, requests go through a cross-Region inference profile (listed in aliases).

What breaks when you move off Claude Sonnet 5.5

  • Defaults

    Requests without a thinking field now run with adaptive thinking.

    Claude Sonnet 5.5 · Claude API, Google Vertex AI ·

  • Parameters

    Thinking type "disabled" returns a 400 error. Send thinking type "between_tools" to turn off up-front thinking.

    Claude Sonnet 5.5 · Claude API, Google Vertex AI ·

  • Parameters

    Forced tool choice (tool_choice "any" or "tool") returns a 400 error.

    Claude Sonnet 5.5 · Claude API, Google Vertex AI ·

Intelligence

Third-party results, credited below
Third-party benchmark scores for Claude Sonnet 5.5
BenchmarkPublisherScoreRankPublished
Arena TextArena1,476 ± 5#19 of 128Oct 8, 2026
GPQA DiamondEpoch AI95.6% ± 1.4%#3 of 108Sep 29, 2026
Arena WebDevArena1,774 ± 8#3 of 69Oct 8, 2026
Arena AgentArena0 ± 0#7 of 35Oct 12, 2026
FrontierMath Tier 4Epoch AI80.5% ± 6.3%#8 of 58Sep 29, 2026
FrontierMath Tiers 1-3Epoch AI88.8% ± 1.9%#7 of 71Sep 29, 2026
OTIS Mock AIME 2024-2025Epoch AI100.0% ± 0.0%#4 of 105Sep 29, 2026
SimpleQA VerifiedEpoch AI46.5% ± 1.6%#29 of 68Sep 29, 2026

Arena (arena.ai), https://arena.ai/leaderboard

Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].

List prices

$ per 1M tokens, with each price’s source
List prices per 1M tokens, in US dollars
PlatformInputCachedOutputIn effectSource
Claude APIclaude-sonnet-5-5$2.00$0.10$10.00Sep 28, 2026CurrentAnthropic: Pricing (opens in a new tab)
Amazon Bedrockanthropic.claude-sonnet-5-5$2.20$0.11$11.00Oct 1, 2026Current · Standard tier, in-Region or geographic cross-Region inference, which Bedrock prices 10% above global cross-Region inference.Amazon Web Services: AWS Price List API: AmazonBedrockFoundationModels, us-east-1 (opens in a new tab)
Google Vertex AIclaude-sonnet-5-5$2.00$0.10$10.00Sep 28, 2026Current · Global endpoint price; regional and multi-region endpoints cost more.Google Cloud: Agent Platform pricing (opens in a new tab)

Change history

ShutdownClaude Sonnet 4.5 shuts down on the Claude APIClaude API6 breaks

Requests to claude-sonnet-4-5-20250929 fail after the shutdown date. Anthropic names Claude Sonnet 5.5 as the replacement.

Platform
Claude API
Announced
  • ParametersClaude 4.7 and later models return a 400 error when temperature, top_p or top_k is set to a non-default value. Remove them before switching.
  • ParametersManual thinking budgets (thinking type "enabled" with budget_tokens) return a 400 error on Claude Sonnet 5.5. Use adaptive thinking and an effort level.
  • ParametersA prefilled final assistant turn returns a 400 error. Claude Sonnet 4.5 accepted one.
  • ParametersForced tool choice (tool_choice "any" or "tool") returns a 400 error on Claude Sonnet 5.5. Use "auto" with strict tools.
  • DefaultsRequests without a thinking field run with adaptive thinking on Claude Sonnet 5.5, so responses can start with thinking blocks.
  • TokenizerThe same text produces about 30% more tokens than on Claude Sonnet 4.5. Recount prompts and revisit max_tokens.

Source: Anthropic, Model deprecations (opens in a new tab); Anthropic, Claude Sonnet 5.5 migration guide (opens in a new tab)

ShutdownClaude Sonnet 4.5 retires on Azure AI FoundryAzure AI Foundry1 break

claude-sonnet-4-5 retires on Foundry. Microsoft lists claude-sonnet-5-5 as the replacement.

Platform
Azure AI Foundry
  • AvailabilityInference requests to retired deployments return 410 Gone.

Source: Microsoft, Model retirement schedule - Microsoft Foundry (opens in a new tab); Microsoft, Microsoft Foundry Models lifecycle and support policy (opens in a new tab)

ReleaseClaude Sonnet 5.5 releasedClaude API, Google Vertex AI3 breaks

Anthropic released Claude Sonnet 5.5 at the Claude Sonnet 5 price, with cache reads at half the earlier rate. Google Cloud lists the same release date.

Platform
Claude API, Google Vertex AI
  • DefaultsRequests without a thinking field now run with adaptive thinking.
  • ParametersThinking type "disabled" returns a 400 error. Send thinking type "between_tools" to turn off up-front thinking.
  • ParametersForced tool choice (tool_choice "any" or "tool") returns a 400 error.

Source: Anthropic, Claude Sonnet 5.5 (opens in a new tab); Anthropic, Claude Sonnet 5.5 migration guide (opens in a new tab); Google Cloud, Claude Sonnet 5.5 on Google Cloud (opens in a new tab); Google Cloud, Gemini Enterprise Agent Platform release notes (opens in a new tab)

ReleaseClaude Sonnet 5.5 available on Amazon BedrockAmazon Bedrock

Bedrock added Claude Sonnet 5.5 as anthropic.claude-sonnet-5-5.

Platform
Amazon Bedrock

Source: Amazon Web Services, Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab)

Built by TeqEngine. Forward-deployed AI engineering, no model to sell. Moving an agent to a new model? Ask for a Next-Model Check.