Claude Opus 4.5 dated snapshot — pinned to 2025-11-01 release.
claude-opus-4-5-20251101 is Anthropic's pinned dated snapshot of Claude Opus 4.5, locked to the November 1 2025 release. It is functionally identical to anthropic/claude-opus-4.5 — the same weights, the same 80.9% SWE-bench Verified score, the same $5/$25 per-million-token pricing — but guaranteed not to drift as Anthropic ships incremental improvements to the un-versioned alias.
Use this model id when you need reproducible, auditable behaviour across deployments: regulated industries, long-running evaluation harnesses, or A/B tests where the control arm must not shift. If you do not have a hard reproducibility requirement, route to the canonical anthropic/claude-opus-4.5 so you automatically receive safe bug fixes. Both ids share the same 200 K context window, image input support, effort parameter (low/medium/high), and manual thinking budget_tokens.
Anthropic's own API exposes this model under the id 'claude-opus-4-5-20251101' (hyphens, no dots). Callers must use the Anthropic SDK or native API format, supply an Anthropic API key, and pass the effort parameter directly via the 'thinking' object or the effort field. The model is identical in capability to the rolling 'claude-opus-4.5' alias at the November 2025 weights.
TheRouter proxies this model through the standard OpenAI-compatible /v1/chat/completions endpoint under the id 'anthropic/claude-opus-4.5-20251101' (dots, slash-separated provider prefix). Callers use any OpenAI SDK, supply a single TheRouter API key, and pass reasoning_effort instead of the native effort field. TheRouter translates the request to Anthropic's API format and returns an OpenAI-shaped response. No Anthropic SDK or direct Anthropic API key is required.
| Type | Rate |
|---|---|
| Input | $5.40 / 1M tokens |
| Output | $27.00 / 1M tokens |
| Pinned release date | 2025-11-01www.anthropic.com ↗ | verified |
| Anthropic model id | claude-opus-4-5-20251101www.anthropic.com ↗ | verified |
| Canonical (rolling) alias | anthropic/claude-opus-4.5docs.anthropic.com ↗ | verified |
| Training cutoff | Not publicly disclosed | unknown |
| Reasoning controls | effort (low/medium/high) + manual thinking budget_tokens (both supported)platform.claude.com ↗ | verified |
| Deployment | Anthropic API, Amazon Bedrock, Google Cloud Vertex AI, Microsoft Azure AI Foundryaws.amazon.com ↗ | verified |
| License | Anthropic Usage Policy (proprietary, API-only) | verified |
| Benchmark | Distribution | Score | Source |
|---|---|---|---|
SWE-bench Verified First model to exceed 80 %. Identical to the claude-opus-4.5 rolling alias result — same weights. | 80.9%% | www.anthropic.com ↗ | |
GPQA Diamond Graduate-level science questions. | 87.0%% | anthropic.com ↗ | |
ARC-AGI-2 Abstract visual reasoning. | 37.6%% | anthropic.com ↗ | |
Prompt injection attack success (Gray Swan) Lowest attack success rate among frontier models tested at release. | 4.7%% | www.anthropic.com ↗ |
Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.
curl https://api.therouter.ai/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $THE_ROUTER_API_KEY" -d '{
"model": "anthropic/claude-opus-4.5-20251101",
"messages": [
{"role": "user", "content": "Summarize the key points from this input."}
]
}'Pin to the November 2025 snapshot for reproducible, auditable results.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.5-20251101",
"messages": [{"role":"user","content":"Refactor this repo to use the new auth middleware."}],
"reasoning_effort": "high"
}'Anthropic launches Opus 4.5 with $5/$25 pricing, new effort parameter, and state-of-the-art coding/agent results. The claude-opus-4-5-20251101 dated snapshot captures this initial release.
AWS announces support for Opus 4.5 in Bedrock the day after release, including global cross-region inference and the new effort parameter.
They point to the same underlying weights as of the November 2025 release. The un-versioned id (claude-opus-4.5) is a rolling alias that Anthropic can silently update with safe improvements. The dated id (claude-opus-4-5-20251101) is frozen at the November 1 2025 snapshot and will never change until Anthropic retires it. Use the dated id for compliance, benchmarking, or A/B control arms; use the rolling id for production traffic that benefits from incremental fixes.
No deprecation date has been announced as of August 2026. Anthropic's policy is to give at least 6 months notice before retiring a pinned model version. Monitor the Anthropic model deprecations page for updates.
Yes — both are supported. You can pass reasoning_effort: 'high' via the OpenAI-compatible endpoint or set an explicit thinking budget with budget_tokens via the Anthropic SDK. This is one feature that later models (Opus 4.7+) removed by eliminating manual budget_tokens, so Opus 4.5 / 4.5-20251101 retains the combined approach.
| source | URL | retrieved | |
|---|---|---|---|
| Pinned release date | www.anthropic.com ↗ | 2026-08-20 | verified |
| Anthropic model id | www.anthropic.com ↗ | 2026-08-20 | verified |
| Canonical (rolling) alias | docs.anthropic.com ↗ | 2026-08-20 | verified |
| Training cutoff | — | — | unknown |
| Reasoning controls | platform.claude.com ↗ | 2026-08-20 | verified |
| Deployment | aws.amazon.com ↗ | 2026-08-20 | verified |
| License | — | — | verified |
| SWE-bench Verified | www.anthropic.com ↗ | 2026-08-20 | verified |
| GPQA Diamond | anthropic.com ↗ | 2026-08-20 | verified |
| ARC-AGI-2 | anthropic.com ↗ | 2026-08-20 | verified |
| Prompt injection attack success (Gray Swan) | www.anthropic.com ↗ | 2026-08-20 | verified |
| Claude Opus 4.5 released — first model above 80 % on SWE-bench Verified | anthropic.com/news ↗ | 2026-08-20 | verified |
| Claude Opus 4.5 available in Amazon Bedrock with global cross-region inference | aws.amazon.com ↗ | 2026-08-20 | verified |
| What is the difference between anthropic/claude-opus-4.5 and anthropic/claude-opus-4.5-20251101? | docs.anthropic.com ↗ | 2026-08-20 | to verify |
| When will claude-opus-4-5-20251101 be deprecated? | docs.anthropic.com ↗ | 2026-08-20 | to verify |
| Does claude-opus-4.5-20251101 support the effort parameter and manual thinking budget_tokens? | platform.claude.com ↗ | 2026-08-20 | to verify |