Claude Opus 4.5
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Updated 2 h ago · first seen 11 Sept 2026
model_01M293VBD8J8KGJNJGF7K9NQVD
- Context
- 200K tokens
- T2 · 4 h ago
- Released
- 24 Nov 2025
- T2 · 4 h ago
Specification
- Family
- Claude
Source:Claude Developer Platform docsT1observed 4 h agohigh
- Release date
- 24 Nov 2025
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Status
- active
Source:Claude Developer Platform docsT1observed 4 h agohigh
- Openness
- proprietary
Source:Claude Developer Platform docsT1observed 4 h agohigh
- Context window
- 200K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Max output
- 64K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Input modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- Claude
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Retirement date
- 24 Nov 2026
Source:Claude Developer Platform docsT1observed 4 h agohigh
- Retirement tentative
- Yes
Source:Claude Developer Platform docsT1observed 4 h agohigh
- File input
- Yes
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Aa median output tokens per second
- 45.5
Source:Artificial AnalysisT2observed 2 h agomedium
- Openrouter id
- anthropic/claude-opus-4.5
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Supported parameters
- include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, verbosity
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
21
Source tiers
T1T25 / 16
Freshest observation
2 h ago
Conflicts
1 flagged
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
No
Artificial Analysis · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 200K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Max output
- 64K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- Claude
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 86.26% | pass^1 | aa_slug=claude-opus-4-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 23.68 | index | aa_slug=claude-opus-4-5 · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 81.01% | accuracy | aa_slug=claude-opus-4-5 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 13.16% | accuracy | aa_slug=claude-opus-4-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 42.99% | accuracy | aa_slug=claude-opus-4-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| MMMU-Pro | 71.21% | accuracy | aa_slug=claude-opus-4-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SWE-bench (full test split) | 52.62% | resolved | date=2025-12-19 · board=Test · system=Sonar Foundation Agent · model_tag=claude-opus-4-5 | 19 Dec 2025 | swebench.comT2 |
| SWE-bench Multilingual | 70.7% | resolved | date=2026-02-13 · board=Multilingual · system=mini-SWE-agent · model_tag=claude-opus-4-5-20251101 | 13 Feb 2026 | swebench.comT2 |
| SWE-bench Verified | 79.2% | resolved | date=2025-12-05 · board=Verified · system=Sonar Foundation Agent · model_tag=claude-opus-4-5 | 5 Dec 2025 | swebench.comT2 |
| SWE-bench Verified | 79.2% | resolved | date=2025-12-15 · board=Verified · system=live-SWE-agent · model_tag=claude-opus-4-5-20251101 | 15 Dec 2025 | swebench.comT2 |
| SWE-bench Verified | 74.4% | resolved | date=2025-11-24 · board=Verified · system=mini-SWE-agent · model_tag=claude-opus-4-5-20251101 | 24 Nov 2025 | swebench.comT2 |
| SWE-bench Verified | 76.8% | resolved | date=2026-02-17 · board=Verified · system=mini-SWE-agent · model_tag=claude-4-5-opus | 17 Feb 2026 | swebench.comT2 |
| Terminal-Bench | 40.91% | accuracy | aa_slug=claude-opus-4-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Anthropic APIanthropic/claude-opus-4.5:batch | $2.5 | $12.5 | $0.25 | — | 200K | 2 h ago | openrouter.aiT2 |
| Anthropic API | $5 | $25 | $0.50 | — | — | 4 h ago | platform.claude.comT1 |
| Anthropic APIanthropic/claude-opus-4.5 | $5 | $25 | $0.50 | — | 200K | 2 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Anthropic API
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Openness
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| proprietary | → current | current | Claude Developer Platform docsT1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Claude Opus 4.5 scores 74.4% on SWE-bench Verified
swebench_leaderboardClaude Opus 4.5 scores 76.8% on SWE-bench Verified
swebench_leaderboardClaude Opus 4.5 scores 79.2% on SWE-bench Verified
swebench_leaderboardClaude Opus 4.5 scores 79.2% on SWE-bench Verified
swebench_leaderboardClaude Opus 4.5 scores 52.62% on SWE-bench (full test split)
swebench_leaderboardClaude Opus 4.5 scores 70.7% on SWE-bench Multilingual
swebench_leaderboardClaude Opus 4.5 scores 40.91% on Terminal-Bench
artificial_analysisClaude Opus 4.5 scores 86.26% on τ²-bench
artificial_analysisClaude Opus 4.5 scores 71.21% on MMMU-Pro
artificial_analysisClaude Opus 4.5 scores 42.99% on IFBench
artificial_analysisClaude Opus 4.5 scores 13.16% on Humanity's Last Exam
artificial_analysisClaude Opus 4.5 scores 81.01% on GPQA
artificial_analysisClaude Opus 4.5 scores 23.68 on Artificial Analysis Intelligence Index
artificial_analysisClaude Opus 4.5: reasoning changed from true to false
ReasoningYes→Noartificial_analysisAnthropic API lists Claude Opus 4.5 at $2.5 in / $12.5 out per 1M tokens
openrouterAnthropic API lists Claude Opus 4.5 at $5 in / $25 out per 1M tokens
openrouterAnthropic API lists Claude Opus 4.5 at $5 in / $25 out per 1M tokens
anthropic
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Claude Developer Platform docs | docs.claude.com/en/docs/about-claude/model-deprecations.md | model_docs | T1· Official | 1 h ago | 1 |
| Claude Developer Platform docs | docs.claude.com/en/docs/about-claude/pricing.md | pricing | T1· Official | 1 h ago | 1 |
| SWE-bench leaderboards | swebench.com/ | leaderboard | T2· Quality secondary | 2 h ago | 1 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 2 h ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 2 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.