Home / Models / Anthropic / Claude Opus 5.5

Claude Opus 5.5 pricing and routing profile

Claude Opus 5.5 from Anthropic lists at $4.00 per million input tokens and $20.00 per million output tokens, with a 1,000,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$4.00

Output, per 1M tokens$20.00

Cached input, per 1M$0.20

Context window1M

Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shape	List cost
Classification or routing (600 tokens in, 10 out)	$2.60
Chat reply (2,000 in, 400 out)	$16.00
Retrieval-augmented answer (8,000 in, 500 out)	$42.00

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Claude Opus 5.5. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Measured by Gimbix

On 400 real BANKING77 customer messages, Claude Opus 5.5 answered 354 correctly (95% interval 85.0%–91.3%), with 0 invalid answers, at $4.03 per 1,000 requests and a median of 3,018 ms. See all 22 models.

Who serves Claude Opus 5.5

Host	Input / output per 1M	Log probabilities	Uptime, last 30 min
Amazon Bedrock	$4.00 / $20.00	no	99.9%
Azure	$4.00 / $20.00	no	99.9%
Google	$4.00 / $20.00	no	99.9%
Claude Platform on AWS	$4.00 / $20.00	no	100.0%
Anthropic	$4.00 / $20.00	no	100.0%
Amazon Bedrock	$4.40 / $22.00	no	—
Amazon Bedrock	$4.40 / $22.00	no	—
Azure	$4.40 / $22.00	no	—
Google	$4.40 / $22.00	no	—
Google	$4.40 / $22.00	no	100.0%
Anthropic	$8.00 / $40.00	no	100.0%

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Claude Opus 5.5 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

Model	Input / output per 1M	Cheaper on a chat reply
Ember-1	$3.00 / $15.00	25%
Kimi K3	$3.00 / $15.00	25%
GLM 5.3 Prime	$2.80 / $8.80	43%
GPT Audio	$2.50 / $10.00	44%
GPT-4o (2024-11-20)	$2.50 / $10.00	44%
GPT-4o (2024-08-06)	$2.50 / $10.00	44%

Compare Claude Opus 5.5

Questions

How much does Claude Opus 5.5 cost?

Claude Opus 5.5 lists at $4.00 per million input tokens and $20.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $16.00 per 1,000 requests.

What is the context window of Claude Opus 5.5?

1,000,000 tokens.

Can a cheaper model replace Claude Opus 5.5?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Claude Opus 5.5 on one half of your requests and make at most three answers worse on the other.