Claude Opus 5.5

anthropic/claude-opus-5.5
NewFlagshipFeatured
VisionToolsJSONReasoning
by Anthropic · 2026-09-22

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. Particularly strong at multi-step changes in large codebases and code review. Multimodal input (text, image, file), 1M-token context, extended thinking, tools and structured outputs.

ctx1M tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT10.00 s
INPUT$4.00/ 1M tokens
OUTPUT$20.00/ 1M tokens
p50 TTFT10.00 s7d
p95 TTFT10.00 s7d
TRAFFIC6.1Mtokens / 7d

Claude Opus 5.5 is Anthropic's flagship model, succeeding Claude Opus 5, for demanding reasoning, coding and long-horizon agentic work. It is particularly strong at multi-step changes in large…

What is Claude Opus 5.5?

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
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="anthropic/claude-opus-5.5",
    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
  • temperature
  • tool_choice
  • tools
  • verbosity

Pricing

Pricing
Input / 1M tokens$4.00
Output / 1M tokens$20.00
Cache read / 1M$0.200
Cache write / 1M$5.00
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $88.00 · With prompt caching $74.70

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.0101

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

Performance

p50 TTFT
10.00 s
Output speed
1784 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

57.6
AA Intelligence
Better than 97% of models compared
#4 of 145
Humanity's Last Exam
61.4
Long-Context Recall
84.7
SciCode
66.9
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News15 mentions · 7dup 15 vs the previous week

How it compares

Claude Opus 5.5Claude Fable 5Claude Fable 5.1Claude Opus 4.7
Input $/M$4.00$10.00$10.00$5.00
Output $/M$20.00$50.00$50.00$25.00
Context1.0M1.0M1.0M1.0M
Quality9/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is Claude Opus 5.5?
It is Anthropic's flagship model, the successor to Claude Opus 5, aimed at demanding reasoning, coding and long-horizon agentic work. It is especially strong at multi-step changes in large codebases and code review.
What inputs does it accept?
Text, images and files, with text output. It serves a 1M-token context window with up to 128K output tokens.
What capabilities does it support?
Extended thinking with configurable reasoning effort (reasoning_effort), function calling / tools, structured (JSON) outputs via response_format, temperature and stop controls, and a verbosity setting.
Which APIs can call it?
Both the Anthropic Messages API (/v1/messages) and the OpenAI-compatible Chat Completions API (/v1/chat/completions). Any Anthropic or OpenAI SDK works by pointing the base URL at OrcaRouter.
How is it priced?
Input is billed at $4 per million tokens and output at $20 per million (USD). Prompt caching is available, with cached input reads billed at a steep discount. See the pricing on this page for the current rate.

Embed this badge

Anthropic: Claude Opus 5.5$4.00/M in10000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-opus-5.5" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-opus-5.5.svg" alt="Anthropic: Claude Opus 5.5 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Opus 5.5](https://www.orcarouter.ai/embed/anthropic/claude-opus-5.5.svg)](https://www.orcarouter.ai/models/anthropic/claude-opus-5.5)

Model card as data

GET /api/public/models/anthropic/claude-opus-5.5Open
Machine-readable:/llms.txt/llms-full.txt