Claude Sonnet 4.5
Shutting down. Claude Sonnet 4.5 shuts down on the Claude API on Nov 30, 2026. Anthropic names Claude Sonnet 5.5 as the replacement.
47 days- Next shutdown
- 47 daysNov 30, 2026 · Claude API
- Arena Text
- 1,456#34 of 128 · Arena
- GPQA Diamond
- 82.3%#58 of 108 · Epoch AI
- List price · $ per 1M
- $3.00 in $15.00 outClaude API · cached input $0.30
- Context window
- 200KMax output 64K tokens
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Claude APIAnthropic: Model deprecations (opens in a new tab) · checked Oct 14, 2026 | claude-sonnet-4-5-20250929Deprecated · also claude-sonnet-4-5 | 47 days | Claude Sonnet 5.5 | |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | claude-sonnet-4-5:1Active | – | 47 days | Claude Sonnet 5.5 |
| Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026af-south-1, ap-east-2, ap-northeast-1, ap-northeast-2, ap-northeast-3, ap-south-1, ap-south-2, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-4, ap-southeast-5, ap-southeast-6, ap-southeast-7, ca-central-1, ca-west-1, eu-central-1, eu-central-2, eu-north-1, eu-south-1, eu-south-2, eu-west-1, eu-west-2, eu-west-3, il-central-1, mx-central-1, sa-east-1, us-east-1, us-east-2, us-west-1, us-west-2 | anthropic.claude-sonnet-4-5-20250929-v1:0Deprecated since Oct 8, 2026 · also au.anthropic.claude-sonnet-4-5-20250929-v1:0, eu.anthropic.claude-sonnet-4-5-20250929-v1:0, global.anthropic.claude-sonnet-4-5-20250929-v1:0, jp.anthropic.claude-sonnet-4-5-20250929-v1:0, us.anthropic.claude-sonnet-4-5-20250929-v1:0 | – | 6 moPaid extended access from Jan 8, 2027 | – |
| Google Vertex AIGoogle Cloud: Claude Sonnet 4.5 on Google Cloud (opens in a new tab) · checked Oct 14, 2026 | claude-sonnet-4-5@20250929Active · also claude-sonnet-4-5 | – | Floor passedNot sooner than | – |
The Models API still reported this model as active, with no deprecation date, when checked.
Version 1 runs on Anthropic infrastructure.
New customers can't use Legacy models on Bedrock, and accounts that stop calling one for 15 days may lose access before end of life.
In us-east-1, requests go through a cross-Region inference profile (listed in aliases).
Public extended access starts on 8 January 2027; the model provider may charge higher prices from then until end of life.
Retires on the Claude API on November 30, 2026. Google lists no shutdown date here; its earliest retirement date has passed.
What breaks when you move off Claude Sonnet 4.5
- Availability
- Availability
- Tooling
- Pricing
- Parameters
- Parameters
- Parameters
- Parameters
- Defaults
- Tokenizer
- Availability
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,456 ± 1 | #34 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 82.3% ± 2.7% | #58 of 108 | Oct 28, 2025 |
| Arena WebDev | Arena | 1,393 ± 4 | #49 of 69 | Oct 8, 2026 |
| FrontierMath Tier 4 | Epoch AI | 2.4% ± 2.4% | #54 of 58 | Jun 11, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 23.9% ± 2.5% | #61 of 71 | Jun 11, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 77.8% ± 6.3% | #64 of 105 | Oct 28, 2025 |
| SimpleQA Verified | Epoch AI | 30.7% ± 1.5% | #54 of 68 | Aug 27, 2026 |
| SWE-bench Verified | Epoch AI | 71.3% ± 2.1% | #19 of 28 | Feb 5, 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
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Claude APIclaude-sonnet-4-5-20250929 | $3.00 | $0.30 | $15.00 | Sep 29, 2025Current | Anthropic: Pricing (opens in a new tab) |
Amazon Bedrockanthropic.claude-sonnet-4-5-20250929-v1:0 | $3.30 | $0.33 | $16.50 | Sep 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-4-5@20250929 | $3.00 | $0.30 | $15.00 | Sep 29, 2025Current · Requests with 200K or more input tokens are billed at long-context rates. 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 reaches end of life on Amazon BedrockAmazon Bedrock4 breaks
Bedrock moved Claude Sonnet 4.5 to Legacy on 8 October 2026. Public extended access starts on 8 January 2027, and requests fail after 8 April 2027.
- Platform
- Amazon Bedrock
- Model
- Claude Sonnet 4.5
- Announced
- AvailabilityNew customers can't use Legacy models, and accounts that stop calling one for 15 days may lose access before the end-of-life date.
- AvailabilityRequests to the model ID fail after the end-of-life date. Bedrock does not migrate applications to another model.
- ToolingYou can't create new Provisioned Throughput or fine-tuning jobs for a Legacy model.
- PricingDuring public extended access, the model provider may charge higher prices until end of life.
Source: Amazon Web Services, Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab); Amazon Web Services, Amazon Bedrock User Guide: Model lifecycle (Legacy) (opens in a new tab)
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
- Model
- Claude Sonnet 4.5
- Replacement
- Claude Sonnet 5.5
- 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
- Model
- Claude Sonnet 4.5
- Replacement
- Claude Sonnet 5.5
- 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)