LLM Reference

Claude Opus 4.5

Released
2025-11-01
Last refreshed
2026-06-29
Status
Researched 44d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool useHighlight

Claude Opus 4.5 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2025-11-01
Context
200k
Architecture
Decoder Only
Knowledge cutoff
2025-12
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Fine-tuned
Created by

Developing safe and ethical AI systems.

San Francisco, California, United States
Founded 2021
Website
Pricing
Output / 1M
$25.00
Input / 1M
$5.00

Cheapest of 6 routes · Anthropic

About

Claude Opus 4.5 is Anthropic's Claude 4.5 model with multimodal text and image input and an optional reasoning mode. It offers a 200K-token context window and scores 80.7 on MMMU.

Claude Opus 4.5 is a proprietary model in the Claude 4.5 family. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Microsoft Foundry, Anthropic, GCP Vertex AI, and 3 more, with the cheapest tracked route listed at $5 input and $25 output per 1M tokens. Headline tracked benchmarks include Massive Multi-discipline Multimodal Understanding 80.7, BFCL 77.5, and SWE-bench Pro 41.8.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
Anthropic$5.00$25.00$2.50 / $12.50-
Serverless
GCP Vertex AI$5.00$25.00--
Serverless
Microsoft Foundry$5.00$25.00-read $0.500 / 5m $6.25 / 1h $10.00
ServerlessProvisioned
OpenRouter$5.00$25.00--
Serverless

Available via routers & gateways(16)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(10)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Massive Multi-discipline Multimodal Understanding80.7https://mmmu-benchmark.github.io/
BFCL77.5https://gorilla.cs.berkeley.edu/leaderboard.html
SWE-bench Pro41.8https://labs.scale.com/leaderboard/swe_bench_pro_public
MMLU PRO88.9https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
Chatbot Arena1466.0Thinking 32Khttps://arena.ai/leaderboard
MMMU Pro73.9official Anthropic (comparison model in Opus 4.6 system card), with image cropping toolhttps://www.anthropic.com/claude-opus-4-6-system-card
Aider Polyglot72.02026-05 (32k thinking)https://aider.chat/docs/leaderboards/
SWE-bench Verified80.9https://www.anthropic.com/news/claude-opus-4-5
Google-Proof Q&A87.0https://www.anthropic.com/news/claude-opus-4-5
ARC-AGI-237.6https://www.anthropic.com/news/claude-opus-4-5

Migration checks

No linked migration route is available for this model yet.

Compare Claude Opus 4.5 with other models

Show all 79 popular comparisonssorted by 7-day search impressions
Claude Opus 4.5 vs Gemini 2.5 Pro102Claude Opus 4.5 vs GLM-599Claude Opus 4.5 vs Grok-379Claude Opus 4.5 vs DeepSeek R1 Distill Llama 70B77Claude Opus 4.5 vs Hunyuan Hy3 Preview72Claude Opus 4.5 vs Claude Opus 4.762Claude Opus 4.5 vs Mistral 7B Instruct v0.347Claude Opus 4.5 vs Llama 3 8B Instruct45Claude Opus 4.5 vs Llama 3 70B Instruct43Claude Opus 4.5 vs GPT-5.3-Codex41Claude Opus 4.5 vs Gemma 4 E2B41Claude Opus 4.5 vs Kimi K2 Thinking40Claude Opus 4.5 vs Claude Haiku 4.539Claude Opus 4.5 vs GPT-4.137Claude Opus 4.5 vs GPT-4.1 Mini36Claude Opus 4.5 vs Claude Opus 4.634Claude Opus 4.5 vs Phi 3.5 MoE Instruct34Claude Opus 4.5 vs o333Claude Opus 4.5 vs Trinity-Large-Thinking32Claude Opus 4.5 vs Gemma 4 26B A4B IT31Claude Opus 4.5 vs Gemma 4 31B IT30Claude Opus 4.5 vs Qwen3-235B-A22B26Claude Opus 4.5 vs o3 Deep Research25Claude Opus 4.5 vs Gemini 3 Pro24Claude Opus 4.5 vs Llama 3.2 1B23Claude Opus 4.5 vs Ling-2.6-1T22Claude Opus 4.5 vs GPT-5.422Claude Opus 4.5 vs DeepSeek V322Claude Opus 4.5 vs Grok 3 Mini20Claude Opus 4.5 vs Llama 3.1 70B Instruct19Claude Opus 4.5 vs GPT-4 Turbo19Claude Opus 4.5 vs Kimi K2 Instruct16Claude Opus 4.5 vs Qwen2.5-7B-Instruct15Claude Opus 4.5 vs GPT-5.215Claude Opus 4.5 vs GLM-5 Turbo15Claude Opus 4.5 vs Qwen3.5-27B15Claude Opus 4.5 vs Qwen2.5-72B14Claude Opus 4.5 vs Qwen2.5-Max14Claude Opus 4.5 vs Qwen3.5-397B-A17B13Claude Opus 4.5 vs GPT-5.2 Codex13Claude Opus 4.5 vs Qwen3.5-122B-A10B12Claude Opus 4.5 vs GLM-5V-Turbo11Claude Opus 4.5 vs Qwen3-Max10Claude Opus 4.5 vs Gemini 2.5 Flash Live API10Claude Opus 4.5 vs Xiaomi MiMo-V2.5-TTS-Series9Claude Opus 4.5 vs Gemini Robotics-ER 1.6 Preview9Claude Opus 4.5 vs Mistral Large 28Claude Opus 4.5 vs o3-pro8Claude Opus 4.5 vs Phi 3.5 Mini Instruct8Claude Opus 4.5 vs Qwen2.5-72B-Instruct7Claude Opus 4.5 vs Llama 3.2 1B Instruct7Claude Opus 4.5 vs Gemini 2.5 Flash6Claude Opus 4.5 vs Qwen3-9B6Claude Opus 4.5 vs Llama 3 Taiwan 70B Instruct6Claude Opus 4.5 vs Gemini 3 Flash Preview6Claude Opus 4.5 vs Llama 2 70B Chat5Claude Opus 4.5 vs StepFun Step-25Claude Opus 4.5 vs Llama 3.1 405B Instruct5Claude Opus 4.5 vs Together AI - Llama 3 8B Lite5Claude Opus 4.5 vs Together AI Qwen2-7B-Instruct4Claude Opus 4.5 vs Mixtral 8x7B4Claude Opus 4.5 vs DeepSeek V3.14Claude Opus 4.5 vs Phi-3 Mini 4k3Claude Opus 4.5 vs Llama 2 13B Chat3Claude Opus 4.5 vs GLM-5 9B3Claude Opus 4.5 vs DeepSeek R1 Zero3Claude Opus 4.5 vs GPT-5 Mini3Claude Opus 4.5 vs GPT-5.5 Instant3Claude Opus 4.5 vs Ling-2.6-Flash3Claude Opus 4.5 vs o3 Mini2Claude Opus 4.5 vs Phi-4 Mini Flash Reasoning2Claude Opus 4.5 vs Mistral Nemotron2Claude Opus 4.5 vs Gemma 7B Instruct2Claude Opus 4.5 vs Llama Guard 4 12B2Claude Opus 4.5 vs Llama Guard 3 1B1Claude Opus 4.5 vs Code Cushman 0021Claude Opus 4.5 vs Code Davinci 0011Claude Opus 4.5 vs DeepSeek R1 05280Claude Opus 4.5 vs Qwen3.5-35B-A3B0

Frequently asked questions

What is the context window of Claude Opus 4.5?

Claude Opus 4.5 has a context window of 200k tokens.

How much does Claude Opus 4.5 cost?

Claude Opus 4.5 pricing ranges from $5/1M to $18.0/1M input tokens depending on the provider.

When was Claude Opus 4.5 released?

Claude Opus 4.5 was released on 2025-11-01.

Which providers offer Claude Opus 4.5?

Claude Opus 4.5 is available from 6 providers: Microsoft Foundry, Anthropic, GCP Vertex AI, AWS Bedrock, OpenRouter, Vercel AI Gateway.

What benchmarks has Claude Opus 4.5 been tested on?

Claude Opus 4.5 has been evaluated on 10 benchmarks, including Massive Multi-discipline Multimodal Understanding, BFCL, SWE-bench Pro, MMLU PRO, Chatbot Arena.