As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/claude-sonnet-4-5/

# Claude Sonnet 4.5

Anthropic, Claude 4 family. Status: deprecated. Type: reasoning model. Released: 2025-09-29. Training cutoff: 2025-01.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Anthropic API (Claude API) | `claude-sonnet-4-5-20250929` (alias `claude-sonnet-4-5`) | https://api.anthropic.com/v1/messages | https://platform.claude.com/docs/en/models/sonnet-4-5/overview |
| AWS Bedrock (InvokeModel) | `anthropic.claude-sonnet-4-5-20250929-v1:0` |  | https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy |
| Google Cloud Vertex AI | `claude-sonnet-4-5@20250929` |  | https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai |
| Microsoft Foundry (Azure) | `claude-sonnet-4-5` |  | https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry |
| Claude Platform on AWS | `claude-sonnet-4-5` |  | https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws |
| OpenRouter | `anthropic/claude-sonnet-4.5` |  | https://openrouter.ai/anthropic/claude-sonnet-4.5 |
| Web app |  |  | https://claude.ai |

## Pricing

- Input: $3 per 1M tokens
- Output: $15 per 1M tokens
- Cache read: $0.30 per 1M tokens
- Unit as published: per 1M tokens (USD); Batch API 50% off
- Source: https://platform.claude.com/docs/en/about-claude/pricing
- Last checked: 2026-10-02

## Specs

- Input: text, image, pdf
- Output: text
- Context window: 200,000 tokens
- Max output: 64,000 tokens
- Open weights: no
- Licence: proprietary

## What it has not seen

- Published training cutoff: 2025-01 (January 2025).
- AI events after it on Post-Cutoff: 2,037 (476 major, 90 historic), as of 2026-11-13.
- Already missing at launch: 43.
- Briefings of the news since January 2025: https://postcutoff.com/briefings/cutoff-2025-01-s.md (short), https://postcutoff.com/briefings/cutoff-2025-01-m.md (medium), https://postcutoff.com/briefings/cutoff-2025-01.md (full).
- Claude Sonnet 4.5 is named in one of our documented cases of cutoff blindness (case 020). https://postcutoff.com/why/020-older-models-reject-matching-briefing/

## What stands out

- 30+ hour autonomous tasks: Anthropic reported it maintained focus for more than 30 hours on complex multi-step tasks. Source: https://www.anthropic.com/news/claude-sonnet-4-5
- SOTA SWE-bench Verified at launch: 77.2% on SWE-bench Verified; billed as 'the best coding model in the world' at release. Source: https://www.anthropic.com/news/claude-sonnet-4-5
- Computer use lead: 61.4% on OSWorld, up from 42.2% for Sonnet 4. Source: https://www.anthropic.com/news/claude-sonnet-4-5

## Notes

Snapshot claude-sonnet-4-5-20250929 (alias claude-sonnet-4-5). Extended thinking only. Training data cutoff Jul 2025. Deprecated on 2026-09-30; retirement on the Claude API scheduled for 2026-11-30 (Anthropic recommends migrating to Claude Sonnet 5.5). Source: https://platform.claude.com/docs/en/release-notes/overview

Legacy Sonnet; migrate to `claude-sonnet-5-5`.

```bash
curl https://api.anthropic.com/v1/messages \
 -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -H "content-type: application/json" \
 -d '{"model":"claude-sonnet-4-5","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'
```

Sources:
- Model page: https://platform.claude.com/docs/en/models/sonnet-4-5/overview
- Announcement: https://www.anthropic.com/news/claude-sonnet-4-5
- Pricing: https://platform.claude.com/docs/en/about-claude/pricing
- Models overview: https://platform.claude.com/docs/en/about-claude/models/overview
- Deprecations: https://platform.claude.com/docs/en/about-claude/model-deprecations

Model page: https://postcutoff.com/m/claude-sonnet-4-5/