Claude Opus 4.5 (Reasoning)
Intelligence
49.7
#29/523
Coding
47.8
#17/429
Math
91.3
#20/265
Speed
64 tok/s
TTFT: 11.64s
Pricing
$5.00 / $25.00
per 1M tokens (in/out)
Claude Opus 4.5 (Reasoning) is Anthropic’s advanced AI model designed for high-level reasoning tasks. It processes at 63.856 tokens per second and is priced at $5 per million input tokens, targeting professional users.
When to Use Claude Opus 4.5 (Reasoning)
✓ Best For
- Complex reasoning tasks
- Mathematical problem solving
- Software development assistance
✗ Not Ideal For
- Basic conversational applications
- High-speed real-time processing
How Claude Opus 4.5 (Reasoning) Compares
Intelligence Index · Higher is better
DeepSeekZ AIAnthropicMiniMaxxAI
Benchmark Profile
Coding Index
OpenAIAnthropicMeta
Output Speed · tok/s
AlibabaAnthropicZ AI
Math Index
OpenAIAnthropicAlibabaNVIDIA
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 49.7 | |
| Coding Index | 47.8 | |
| Math Index | 91.3 | |
| MMLU-Pro | 895% | |
| GPQA | 866% | |
| LiveCodeBench | 871% | |
| HLE | 284% | |
| SciCode | 49.5% | |
| IFBench | 58% | |
| LCR | 74% | |
| TerminalBench Hard | 47% | |
| Tau2 | 89.5% | |
| AIME 2025 | 91.3% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Claude Opus 4.5 (Reasoning) released?
Claude Opus 4.5 (Reasoning) was released on November 24, 2025.
Who created Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) was created by Anthropic.
How intelligent is Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) scores 50 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 31).
How fast is Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) generates output at 46.8 tokens per second (based on Anthropic's API), which is below average compared to other reasoning models in a similar price tier (median: 67.8 t/s).
What is the latency of Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) has a time to first token (TTFT) of 16.71s (based on Anthropic's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 2.57s).
How much does Claude Opus 4.5 (Reasoning) cost?
Claude Opus 4.5 (Reasoning) costs $5.00 per 1M input tokens (at the higher end, median: $1.35) and $25.00 per 1M output tokens (at the higher end, median: $8.40), based on Anthropic's API.
What is Claude Opus 4.5 (Reasoning) API pricing?
Claude Opus 4.5 (Reasoning) costs $5.00 per 1M input tokens and $25.00 per 1M output tokens (based on Anthropic's API). For a blended rate (3:1 input to output ratio), this is $10.00 per 1M tokens. Pricing may vary by provider.
How verbose is Claude Opus 4.5 (Reasoning)?
When evaluated on the Intelligence Index, Claude Opus 4.5 (Reasoning) generated 72M output tokens, which is at the higher end compared to other reasoning models in a similar price tier (median: 30M).
Is Claude Opus 4.5 (Reasoning) a reasoning model?
Yes, Claude Opus 4.5 (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Claude Opus 4.5 (Reasoning) support?
Claude Opus 4.5 (Reasoning) supports text and image input.
What output modalities does Claude Opus 4.5 (Reasoning) support?
Claude Opus 4.5 (Reasoning) supports text output.
Can Claude Opus 4.5 (Reasoning) process images?
Yes, Claude Opus 4.5 (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Claude Opus 4.5 (Reasoning) multimodal?
Yes, Claude Opus 4.5 (Reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) has a context window of 200k tokens. This determines how much text and conversation history the model can process in a single request.
Is Claude Opus 4.5 (Reasoning) open source?
No, Claude Opus 4.5 (Reasoning) is proprietary. The model weights are not publicly available.
