Claude Opus 4.5

anthropic/claude-opus-4.5
VisionToolsJSONReasoning
by Anthropic · 2025-11-24

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...

ctx200K tokens
Max output64K
Inputfile + image + text
Outputtext
p50 TTFT1.92 s
INPUT$5.00/ 1M tokens
OUTPUT$25.00/ 1M tokens
p50 TTFT1.92 s7d
p95 TTFT5.00 s7d
TRAFFIC1.9Mtokens / 7d

Claude Opus 4.5 is Anthropic’s flagship language model, built for tasks that benefit from deep reasoning, large context windows, and high output lengths. It processes text, images, and file uploads,…

What is Claude Opus 4.5 and who should use it?

What input types does Claude Opus 4.5 support?

How does the 200K context window affect use cases?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="anthropic/claude-opus-4.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • stop
  • stream
  • structured_outputs
  • temperature
  • thinking
  • tool_choice
  • tools
  • top_k
  • top_p

Pricing

Input / 1M tokens$5.00
Output / 1M tokens$25.00
Cache read / 1M$0.500
Cache write / 1M$6.25
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $110 · With prompt caching $94.25

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.0126

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.92 s
Output speed
92.6 tok/s
p95 TTFT
5.00 s
Error rate
0%

Public benchmarks

42.9
AA Coding
Better than 53% of models compared
#49 of 106
43.1
AA Intelligence
Better than 47% of models compared
#57 of 110
62.7
AA Math
Better than 52% of models compared
#39 of 81
AIME 2025
62.7
GPQA Diamond
81.0
Humanity's Last Exam
12.9
IFBench
43.0
LiveCodeBench
73.8
Long-Context Recall
65.3
MMLU-Pro
88.9
SciCode
47.0
TerminalBench Hard
40.9
τ²-Bench
86.3
Source: artificialanalysis.ai

How it compares

Claude Opus 4.5Claude Fable 5Claude Opus 4.7Claude Opus 4.8
Input $/M$5.00$10.00$5.00$5.00
Output $/M$25.00$50.00$25.00$25.00
Context200K1.0M1.0M1.0M
Quality8/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does Claude Opus 4.5 cost on OrcaRouter?
Pricing is $5.00 per 1 million input tokens and $25.00 per 1 million output tokens, billed at the provider’s rate with zero markup. There are no additional fees.
What is the context window for Claude Opus 4.5?
The context window is 200,000 tokens (input side). The model can generate up to 64,000 tokens per completion.
What are the main strengths of Claude Opus 4.5?
It excels at complex reasoning, multi‑step problem solving, code generation, and long‑document analysis. It scores 88.9 on MMLU‑Pro and supports text, image, and file inputs.
How does Claude Opus 4.5 compare to other models on OrcaRouter?
It is Anthropic’s largest model, offering higher accuracy but higher cost and latency than smaller options like Claude Sonnet or Haiku. It competes with GPT‑4 and Gemini Ultra on benchmarks.
What data handling policies apply to Claude Opus 4.5 via OrcaRouter?
Data handling follows Anthropic’s policies for the model and OrcaRouter’s privacy policy. No specific data retention rules were provided in the facts. Check both providers for details.
How do I call Claude Opus 4.5 through OrcaRouter’s API?
Use the OpenAI‑compatible API at https://api.orcarouter.ai/v1 with model ID "anthropic/claude-opus-4.5". Include your OrcaRouter API key in the Authorization header.
Can I use images and files as input?
Yes. Claude Opus 4.5 supports file, image, and text modalities. Include them in the content array using the standard multimodal format (e.g., image_url).
What is the maximum output length?
The maximum output is 64,000 tokens per API call. Set the max_tokens parameter accordingly.
Is there caching available to reduce costs?
The provided facts do not mention caching for this model. Check OrcaRouter’s documentation for any caching options.
How do I migrate from Anthropic’s direct API to OrcaRouter?
Change your base URL to https://api.orcarouter.ai/v1, replace your API key with an OrcaRouter key, and adapt message formats to the OpenAI‑compatible schema.

Embed this badge

Anthropic: Claude Opus 4.5$5.00/M in1920ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-opus-4.5" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-opus-4.5.svg" alt="Anthropic: Claude Opus 4.5 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Opus 4.5](https://www.orcarouter.ai/embed/anthropic/claude-opus-4.5.svg)](https://www.orcarouter.ai/models/anthropic/claude-opus-4.5)

Model card as data

GET /api/public/models/anthropic/claude-opus-4.5Open
Machine-readable:/llms.txt/llms-full.txt