Claude Opus 4.5 API

Claude Opus 4.5 is Anthropic's most intelligent model, a hybrid reasoning system for production-grade coding, agent workflows, and complex analysis with a 200K context window. Access it through EvoLink's unified API.

Using coding CLIs? Run Claude 4.5 Opus via EvoCode — One API for Code Agents & CLIs. (View Docs)

PRICING

PLAN	CONTEXT WINDOW	MAX OUTPUT	INPUT	OUTPUT	CACHE WRITE	CACHE READ
Claude Opus 4.5	200.0K	64.0K	$4.13-17% $5.00Official Price	$21.25-15% $25.00Official Price	$5.31-15% $6.25Official Price	$0.425-15% $0.500Official Price
Claude Opus 4.5 (Beta)	200.0K	64.0K	$1.30-74% $5.00Official Price	$6.50-74% $25.00Official Price	$1.63-74% $6.25Official Price	$0.130-74% $0.500Official Price

Web Search Tool

Server-side web search capability

$0.011/search

Pricing Note: Price unit: USD / 1M tokens

Cache Hit: Price applies to cached prompt tokens.

Two ways to run Claude Opus 4.5 — pick the tier that matches your workload.

· Claude Opus 4.5: the default tier for production reliability and predictable availability.
· Claude Opus 4.5 (Beta): a lower-cost tier with best-effort availability; retries recommended for retry-tolerant workloads.

Claude Opus 4.5 API — Anthropic's most intelligent model

Claude Opus 4.5 (Claude 4.5 Opus) pairs hybrid reasoning with a 200K context window and up to 64K output tokens for advanced coding, research, and agentic workflows.

What can you build with the Claude Opus 4.5 API?

Frontier-Grade Reasoning

Solve multi-step planning, financial analysis, and technical strategy with Opus 4.5's hybrid reasoning. The 200K context window lets you process large specs, logs, or contracts in one pass, then generate a defensible rationale and prioritized actions.

Explore reasoning

Production-Grade Coding

Use Anthropic's flagship model for architecture, refactors, code review, and bug fixing. With up to 64K output tokens, generate long diffs, test suites, migration plans, and detailed implementation steps that are easier to execute.

Try coding

Agentic Workflows & Tool Use

Build reliable agents that plan, call tools, and maintain context across multi-step tasks. Opus 4.5 is designed for advanced agents and tool-heavy workflows that require precision, persistence, and predictable outputs.

Build agents

Why teams choose the Claude Opus 4.5 API on EvoLink

Get Anthropic's flagship intelligence with stable model IDs, prompt caching, and unified routing through EvoLink's single API key.

Flagship reasoning for the hardest work

Opus 4.5 is built for complex planning, deep analysis, and long-horizon tasks where quality matters more than speed.

Production stability with versioned IDs

Use `claude-opus-4-5` for fast iteration, or pin `claude-opus-4-5-20251101` to keep behavior consistent across releases.

Cost control without sacrificing quality

Prompt caching supports 5-minute and 1-hour caches, and cache hits are billed at 0.1x the base input rate to reduce repeat costs.

How to integrate the Claude Opus 4.5 API

Connect through EvoLink, choose your model ID, and tune cost vs. quality in minutes.

Step 1 — Create your EvoLink API key

Step 2 — Select the model ID

Use `claude-opus-4-5` for the latest alias or pin `claude-opus-4-5-20251101` to lock behavior for production.

Step 3 — Optimize quality and cost

Claude Opus 4.5 supports the `effort` parameter to trade off thoroughness and token usage, and prompt caching to lower repeat costs.

View API Docs

Claude Opus 4.5 API capabilities

Key specs and model features for production use

Context

200K Context Window

Read large documents or codebases in a single request without chunking.

Capacity

64K Max Output

Generate long-form answers, plans, and code without early truncation.

Intelligence

Hybrid Reasoning + Extended Thinking

Combine fast responses with deeper reasoning when tasks become complex.

Multimodal

Vision + Multilingual Input

Accept text and image inputs with strong multilingual understanding.

Efficiency

Prompt Caching Rates

Cache writes and reads are priced separately; cache hits are billed at 0.1x the base input price.

Reliability

Stable IDs & Aliases

Aliases auto-upgrade to the newest snapshot, while versioned IDs keep results consistent.

Claude Opus 4.5 API - FAQ

Everything you need to know about the product and billing.

Claude Opus 4.5 supports a 200K token context window and up to 64K output tokens in a single request, making it suitable for long documents, multi-step workflows, and large codebases.

Use the versioned Claude API ID `claude-opus-4-5-20251101` for stable production behavior, or the alias `claude-opus-4-5` for the latest snapshot during iteration. Aliases typically move to the newest snapshot within about a week of release, so pin IDs for regulated or reproducible workflows.

Base pricing is $5 per million input tokens and $25 per million output tokens (MTok = one million tokens). Prompt caching is billed separately with cache writes and cache hits priced per model. Provider pricing can differ on Bedrock or Vertex AI.

For Opus 4.5, cache writes are $6.25/MTok (5-minute) and $10/MTok (1-hour). Cache hits are $0.50/MTok, which is 0.1x the base input price. Use caching for stable system prompts or repeated long context.

Claude Opus 4.5 is the only Claude 4.5 model that supports the `effort` parameter. You can set low, medium, or high effort to trade off response thoroughness and token usage for each request, which helps balance cost and latency.

Claude Opus 4.5 is available via the Anthropic API and on AWS Bedrock and Google Vertex AI. Official IDs include `claude-opus-4-5-20251101` (Claude API), `anthropic.claude-opus-4-5-20251101-v1:0` (Bedrock), and `claude-opus-4-5@20251101` (Vertex AI). EvoLink can route to the provider you choose.

Yes. All current Claude models support text and image input with multilingual capabilities, so you can combine documents, screenshots, and visuals in one request.

The models overview lists a reliable knowledge cutoff of May 2025 for Opus 4.5, with a broader training data cutoff of August 2025.