Inference
EN
Anthropic

Claude Opus 4.1

Claude Opus 4.1 is a model from Anthropic. 16 benchmarks count toward its index, in 6 categories.

  • Input: image · text · file
  • Released 2025-08
RankedEnough results for an index.
IndexAll categories, out of 100.47.5±5.0Median 51.0
CoverageIndex weight that has results.90%
SpeedOutput tokens per second.12/sMedian 67/s
First tokenSeconds to the first output token.4.7 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$15.00batch $7.50Median $0.60
Output / 1MUS dollars per 1M output tokens.$75.00batch $37.50 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.200KMedian 262K
EloLMArena rating and rank.1419±3 #124Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
anthropic/claude-opus-4.1
Max outputMaximum output tokens per request.
32K
Knowledge cutoffLast date of training data.
31 Jan 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
No
Cache read / 1MUS dollars per 1M cached tokens.
$1.50
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DatabricksCloud$15.00$75.00200K
OpenRouterRouter$15.00$75.00200K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted48.7—
CodingCode writing and repair.3 counted48.2151 / 209
ReasoningLogic problems and puzzles.2 counted55.583 / 227
MultimodalTasks with images and text.1 counted51.1—
KnowledgeFacts and expert knowledge.2 counted49.4138 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.7 counted42.0119 / 168

Results

16 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
τ²-bench RetailAgentic82.4%5 / 23
MMLU ProKnowledge87.2% ±0.332 / 135
MATH 500Math93.0% ±1.117 / 59
GPQA diamond · Epoch AIKnowledge76.8% ±3.099 / 217
FrontierMath-Tier-4-2025-07-01-PrivateMath4.2% ±2.926 / 55
IOI v1Coding12.5% ±4.932 / 61
Mystery Game PuzzlesReasoning21.0% ±4.143 / 80
OTIS Mock AIME 2024-2025Math64.4% ±7.2109 / 200
FrontierMath-2025-02-28-PrivateMath6.6% ±1.541 / 69
SWE-Bench verified · Epoch AICoding73.3% ±2.020 / 32
MMMU ProMultimodal73.7% ±1.158 / 92
AIMEMath44.2% ±1.765 / 95
GPQA Diamond · Vals AIKnowledge70.0% ±2.394 / 135
LiveCodeBenchCoding64.6% ±1.1101 / 142
τ²-bench AirlineAgentic56.0%17 / 22
FrontierMath-Tier-4-v2-PrivateMath2.4% ±2.465 / 72
EBR-benchReasoning7.9%28 / 31
FrontierMath-Tiers-1-3-v2-PrivateMath12.6% ±2.084 / 90
MGSMMultilingual94.2% ±1.55 / 74
MedQAHealthcare92.5% ±0.230 / 95
LegalBenchLegal83.5% ±0.454 / 149
MedCodeHealthcare41.4% ±2.053 / 106
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
TaxEval v2Finance71.5% ±0.978 / 143
MortgageTaxFinance61.1% ±1.063 / 97
MedScribeHealthcare71.8% ±2.092 / 109

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedSierra ResearchMITEpoch AICC BYmodels.devMIT

History

5 releases
Index48.4 → 47.5
23 Oct 202612 Nov 2026
Output / 1M$75.00 → $75.00
23 Oct 202612 Nov 2026

Questions

How much does Claude Opus 4.1 cost?
$15.00 per 1M input tokens, $75.00 per 1M output tokens.
How good is Claude Opus 4.1?
Its index is 47.5 out of 100. That is place 164 of 283 ranked models.
What is Claude Opus 4.1 best at?
Reasoning: 55.5 out of 100, place 83 of 227.
How fast is Claude Opus 4.1?
12 output tokens per second, 4.7 s to the first token.
What is the context window of Claude Opus 4.1?
200K tokens.
When was Claude Opus 4.1 released?
August 2025.

Badge

Claude Opus 4.1 on Inference360: place 164 of 283, index 47.5
HTML
<a href="https://inference360.ai/models/anthropic-claude-opus-4-1"><img src="https://inference360.ai/badges/anthropic-claude-opus-4-1.svg" alt="Claude Opus 4.1 on Inference360: place 164 of 283, index 47.5" height="20"></a>
Markdown
[![Claude Opus 4.1 on Inference360: place 164 of 283, index 47.5](https://inference360.ai/badges/anthropic-claude-opus-4-1.svg)](https://inference360.ai/models/anthropic-claude-opus-4-1)

Compare with

Grok 4.1 Fast (Reasoning)47.3Gemma 4 31B47.9Claude Sonnet 4.547.9Claude Sonnet 4.5 Thinking53.8

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Anthropic

All models
Claude 4.1 Opus Thinking47.0Claude 4.1 OpusUnrankedClaude Sonnet 4.5 Thinking53.8Claude Sonnet 4.547.9Claude Haiku 4.5 Thinking43.5