Anthropic model product
Claude Opus 4.1
1 is a hybrid reasoning model from Anthropic for coding and AI agent tasks, with a 200K context window and support for up to 32K output tokens.
Updated Sep 8, 2026. Default version: Claude Opus 4.1
LLMBoard Score51.1Claude Opus 4.1
Coverage0%8 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Opus 4.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Opus 4.1 Benchmark Results
Benchmark scores for Claude Opus 4.1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMMU (validation) | Score77.10% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score82.40% | Rank02 | Participants25 | Percentile95.83% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score43.30% | Rank05 | Participants25 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score89.50% | Rank10 | Participants49 | Percentile81.25% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score56.00% | Rank10 | Participants23 | Percentile59.09% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search | Score1,148.28 rating | Rank21 | Participants28 | Percentile25.93% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,167.11 rating | Rank21 | Participants28 | Percentile25.93% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,153.88 rating | Rank22 | Participants28 | Percentile22.22% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score74.50% | Rank39 | Participants113 | Percentile66.07% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,449.71 rating | Rank52 | Participants210 | Percentile75.60% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,388.96 rating | Rank64 | Participants97 | Percentile34.38% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,434.57 rating | Rank71 | Participants121 | Percentile41.67% | EvidenceA | Evaluated |
| BenchmarkAIME 2025 | Score78.00% | Rank78 | Participants119 | Percentile34.75% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,419.02 rating | Rank83 | Participants210 | Percentile60.77% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score80.90% | Rank92 | Participants247 | Percentile63.01% | EvidenceC | Evaluated |
Claude Opus 4.1 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenasearch | Categoryoverall | Rank21 | Rating / score1,148.28 | Votes76,933 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank21 | Rating / score1,167.11 | Votes76,933 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank21 | Rating / score1,467.13 | Votes2,276 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank22 | Rating / score1,153.88 | Votes59,889 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank24 | Rating / score1,484.77 | Votes11,223 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank30 | Rating / score1,510.92 | Votes3,034 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank30 | Rating / score1,443.92 | Votes629 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank32 | Rating / score1,444.70 | Votes6,734 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank33 | Rating / score1,459.15 | Votes12,913 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank33 | Rating / score1,421.55 | Votes1,096 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank34 | Rating / score1,479.75 | Votes9,723 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank34 | Rating / score1,455.22 | Votes11,223 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank34 | Rating / score1,469.93 | Votes3,825 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank35 | Rating / score1,438.56 | Votes3,333 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank35 | Rating / score1,512.28 | Votes9,723 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank36 | Rating / score1,472.41 | Votes8,346 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank38 | Rating / score1,449.21 | Votes4,160 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank39 | Rating / score1,434.08 | Votes8,934 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank40 | Rating / score1,446.76 | Votes2,276 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank40 | Rating / score1,479.96 | Votes24,504 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank40 | Rating / score1,486.95 | Votes10,531 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank41 | Rating / score1,436.61 | Votes12,913 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank41 | Rating / score1,462.72 | Votes2,563 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank41 | Rating / score1,444.47 | Votes10,859 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank42 | Rating / score1,481.90 | Votes3,349 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank42 | Rating / score1,492.79 | Votes16,444 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank43 | Rating / score1,484.36 | Votes2,440 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank43 | Rating / score1,451.42 | Votes1,041 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank43 | Rating / score1,476.17 | Votes2,627 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank44 | Rating / score1,390.03 | Votes862 | ObservationsN/A | Result date |
Claude Opus 4.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $13 input, $64 output per 1M via Poe
- Tracked offerings
- 22
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDanthropic/claude-opus-4.1 | Regionglobal | Input / 1M$13 | Output / 1M$64 | Context196.6K | Updated |
| ProviderJiekou.AI | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$13.5 | Output / 1M$67.5 | Context200K | Updated |
| ProviderNanoGPT | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderVertex | Provider model IDclaude-opus-4-1@20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-opus-4.1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-opus-4-1@20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-claude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-opus-4-1-20250805-v1:0 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderFastRouter | Provider model IDanthropic/claude-opus-4.1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-opus-4.1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderHelicone | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderNeon | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderOpenCode Zen | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderRequesty | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderAzure | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-opus-4.1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderPioneer | Provider model IDclaude-opus-4-1 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderAbacus | Provider model IDclaude-opus-4-1-20250805 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
Claude Opus 4.1 Runtime Performance
Provider-specific output speed and catalog latency for Claude Opus 4.1. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed100.00 tok/s | Catalog Latency0.50 s | Max Input200K | Max Output32K | Updated |
| ProviderGoogle | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input200K | Max Output32K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Opus 4.1 Specifications
Technical details for the model's default version.
- Version
- Claude Opus 4.1
- Released
- Aug 5, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 32K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Opus 4.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Opus 4.1 | Released | LLMBoard51.14 | ParametersN/A | Context200K | Max output32K | Open weightsNo | LicenseProprietary |
Models similar to Claude Opus 4.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 4.5
Anthropic
AN
Claude Opus 4
Anthropic
AN
Claude Haiku 4.5
Anthropic
AN
Claude Sonnet 4
Anthropic
AN
Claude Sonnet 3.7
Anthropic
AN
Claude Opus 4.5
Anthropic
What is Claude Opus 4.1?
Key information about Claude Opus 4.1 and its available data.
1 is a large language model from Anthropic that supports extended thinking, coding, agentic search and research, and content generation. 5% on SWE-bench Verified and can provide either instant responses or user-facing summaries of step-by-step reasoning.
Data as of 2026-09-08.
FAQ
Common questions about Claude Opus 4.1.
When was Claude Opus 4.1 released?
Claude Opus 4.1's default version was released on Aug 5, 2025.
How much does Claude Opus 4.1 cost?
No official standard PAYG price is currently available for Claude Opus 4.1. The lowest tracked third-party offer starts at $13 input and $64 output via Poe.
Who created Claude Opus 4.1?
Claude Opus 4.1 was created by Anthropic.
What is the context window for Claude Opus 4.1?
The default version has a 200K token context window.
Is Claude Opus 4.1 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Opus 4.1?
22 provider offerings are linked to the default version.