# Claude Opus 5.5

> Claude Opus 5.5 is Anthropic's new recommended flagship, replacing Claude Opus 5 as the model Anthropic suggests starting with for most workloads. It is built for long-running agentic coding and knowledge work: multi-file refactors, extended tool-use loops, and analysis that needs a large codebase or document set in view at once. It takes a 1M-token context window and vision input, with adaptive thinking always on and a default reasoning effort of "medium."

Canonical: https://routemux.com/anthropic/claude-opus-5-5
Provider: Anthropic

## Key facts

| Field | Value |
| --- | --- |
| Model ID | anthropic/claude-opus-5-5 |
| Official model ID | claude-opus-5-5 |
| Context window | 1M |
| Max output | 8K |
| Input modalities | text, image |
| Output modalities | text |
| Capabilities | Vision, Reasoning, Tool Calling, Coding, Cache, Paid Cache Write, Strip Sampling Params |
| Upstream release | 2026-09-22 |
| Availability | available |

## Pricing

- RouteMux input: $1.12 per 1M tokens
- RouteMux output: $5.6 per 1M tokens
- Official input: $4 per 1M tokens
- Official output: $20 per 1M tokens
- Cache read: $0.056 per 1M tokens
- Cache write: $1.4 per 1M tokens
- Saving vs official: 72%
- Official price source: anthropic_x0.28, verified 2026-09-23

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- anthropic_messages

## What is Claude Opus 5.5

Claude Opus 5.5 is Anthropic's new recommended flagship, replacing Claude Opus 5 as the model Anthropic suggests starting with for most workloads. It is built for long-running agentic coding and knowledge work: multi-file refactors, extended tool-use loops, and analysis that needs a large codebase or document set in view at once. It takes a 1M-token context window and vision input, with adaptive thinking always on and a default reasoning effort of "medium."

Through RouteMux it costs $1.12 per 1M input tokens against Anthropic's $4, and $5.60 per 1M output against $20 — the same model and the same Anthropic Messages API, routed through one key alongside every other model in the catalog. Failed and timed-out requests are not billed. Prompt caching is priced separately: reads are $0.056 per 1M tokens and writes are $1.40 (5-minute) or $2.24 (1-hour) per 1M tokens. Notably, cache reads on Opus 5.5 are billed at 5% of the base input rate, where most Claude models use 10% — caching pays off faster here than on Opus 5 or Sonnet 5.

## Key capabilities

- **1M-token context** — Enough to hold a mid-sized repository or a full document set in a single request, so long-horizon tasks do not need retrieval plumbing to get started.
- **Cheaper than Opus 5** — Input and output pricing is 20% below Claude Opus 5, while Anthropic reports comparable quality at default settings on typical agentic workloads.
- **Cache reads at 5%** — Cache reads cost $0.056 / 1M against a $1.12 base rate — half the 10% ratio most Claude models use for cache reads.
- **Vision input and tool calling** — Accepts images alongside text, and supports native function calling for agentic loops — screenshots, diagrams, and tool results all go in the same conversation.

## Other variants in this family

- Claude Opus 5 (`anthropic/claude-opus-5`)
- Claude Opus 4.7 (`anthropic/claude-opus-4.7`)
- Claude Opus 4.6 (`anthropic/claude-opus-4.6`)
- Claude Opus 4.8 (`anthropic/claude-opus-4.8`)

## Sources

- [Anthropic — Models overview](https://platform.claude.com/docs/en/about-claude/models/overview)
- [Anthropic — Pricing](https://platform.claude.com/docs/en/about-claude/pricing)

_Content reviewed by Jerry Fan on 2026-09-23._