Claude Opus 5

anthropic/claude-opus-5
NewFeatured
VisionToolsJSONReasoning
by Anthropic · 2026-07-24

Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work — the most capable model in the Opus line to date. It is especially strong at end-to-end software engineering, code review and bug finding, and visual analysis, and is built to stay coherent across very long, multi-step agentic sessions with heavy tool use. It accepts text, image, and file inputs with text output, serves a 1M-token context window with up to 128K output tokens, and supports adaptive reasoning with configurable effort. Opus 5 uses Anthropic's adaptive thinking design: instead of sampling parameters like temperature or top_p, callers dial depth through reasoning effort, and the model allocates thinking automatically. It speaks both the OpenAI chat-completions format and Anthropic's native Messages API (/v1/messages), supports structured outputs, verbosity control, and native tool calling, and is a strong default for production coding agents, deep research, and complex automation where correctness and judgment matter most.

ctx1M tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT5.00 s
INPUT$5.00/ 1M tokens
OUTPUT$25.00/ 1M tokens
p50 TTFT5.00 s7d
p95 TTFT10.00 s7d
TRAFFIC2.4Ktokens / 7d

Claude Opus 5 is a large language model developed by Anthropic, positioned as the most capable model in their lineup. It is designed for tasks that require deep reasoning, broad context…

What is Claude Opus 5?

Who should use Claude Opus 5?

What input modalities does Claude Opus 5 support?

How does the 1 million token context window benefit users?

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-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • stop
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Pricing

Input / 1M tokens$5.00
Output / 1M tokens$25.00
Cache read / 1M$0.500
Cache write / 1M$10.00
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
5.00 s
Output speed
26.2 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

78.0
AA Coding
Better than 99% of models compared
#1 of 123
60.7
AA Intelligence
Better than 98% of models compared
#2 of 125
GPQA Diamond
93.2
Humanity's Last Exam
52.6
Long-Context Recall
70.0
SciCode
55.7
tau_banking
30.3
terminalbench_v2_1
89.1
Source: artificialanalysis.ai

How it compares

Claude Opus 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
Context1.0M1.0M1.0M1.0M
Quality10/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use Claude Opus 5 through OrcaRouter?
The cost is $5.00 per 1 million input tokens and $25.00 per 1 million output tokens, billed at the exact Anthropic provider rate with zero markup from OrcaRouter. There are no additional fees or commitments.
What is the context window size for Claude Opus 5?
Claude Opus 5 has a context window of 1,000,000 tokens (1 million tokens). It can also generate up to 128,000 tokens in a single response.
What are the main strengths of Claude Opus 5?
Its main strengths are its large context window, ability to process text, image, and file inputs, and high reasoning capability. It is Anthropic's most capable model for complex tasks requiring deep understanding over long inputs.
How does Claude Opus 5 compare to other Anthropic models?
Claude Opus 5 is Anthropic’s flagship model, more capable than Sonnet or Haiku. It has the largest context window and highest reasoning accuracy, but also the highest cost and latency. Cheaper models are better for simpler tasks.
How is data handled when using Claude Opus 5 on OrcaRouter?
OrcaRouter forwards your requests to Anthropic's API without storing them or modifying the content. Anthropic's data handling policies apply for data sent to their API. OrcaRouter does not log or retain message content beyond what is required for API operation.
How do I call Claude Opus 5 via an OpenAI-compatible API?
Use the base URL https://api.orcarouter.ai/v1 and set the model ID to "anthropic/claude-opus-5". Use a standard OpenAI chat completions request format with your OrcaRouter API key in the Authorization header.
Does OrcaRouter add any latency or markup?
OrcaRouter passes through requests to Anthropic's API with zero markup on pricing. It may add minor network latency due to routing, but does not introduce significant additional delay. Streaming is supported to minimize perceived latency.
Can I use Claude Opus 5 for multimodal tasks like image analysis?
Yes, Claude Opus 5 supports input modalities of text, image, and file. You can include images in your prompt using the OpenAI-compatible schema with content parts of type image_url. The model can analyze and reason about image content.

Embed this badge

Anthropic: Claude Opus 5$5.00/M in5000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-opus-5" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-opus-5.svg" alt="Anthropic: Claude Opus 5 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Opus 5](https://www.orcarouter.ai/embed/anthropic/claude-opus-5.svg)](https://www.orcarouter.ai/models/anthropic/claude-opus-5)

Model card as data

GET /api/public/models/anthropic/claude-opus-5Open
Machine-readable:/llms.txt/llms-full.txt