What is the effort parameter in Claude Opus 4.5 and how does it work?

The effort parameter controls how much token usage the model applies when responding to a request. It defaults to high, affects all token types, and is set independently of the thinking budget via `providerOptions.anthropic.effort` in the AI SDK.

How do I configure the effort parameter through AI Gateway?

Under `providerOptions.anthropic` in your AI SDK v5 call, pass an `effort` level of `low`, `medium`, or `high` alongside the model string `anthropic/claude-opus-4.5`.

What agentic capabilities does Opus 4.5 excel at specifically?

Difficult coding tasks, agentic workflows combining computer use and tool use, and complex multi-step problem solving. The model handles tasks requiring sustained reasoning across long contexts and multi-turn interactions.

How does effort differ from the thinking budget?

They are independent parameters. The effort parameter controls overall token usage across all token types; the thinking budget specifically controls extended reasoning tokens. You can set both separately to tune the cost-quality tradeoff.

What vision improvements does Opus 4.5 include?

Opus 4.5 includes improvements in general intelligence and visual reasoning, handling image analysis, diagram interpretation, and document understanding with stronger accuracy than previous Opus versions.

Does Opus 4.5 support the 1M token context window?

No. The 1M token context window came to Opus models with Claude Opus 4.6.

Is Claude Opus 4.5 suitable for frontend web development work?

Yes, frontend coding and design for developing real-world web applications is specifically listed as an established strength of this model.

Anthropic

Claude Opus 4.5

Claude Opus 4.5 adds an effort parameter for token-usage control and excels at difficult coding, agentic workflows with computer use and tool use, frontend coding, and real-world web app development, with improvements in general intelligence and vision over previous Opus iterations. Your use is subject to Anthropic's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $5, Output $25, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'anthropic/claude-opus-4.5',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Claude Opus 4.5 by Anthropic. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Claude Opus 4.5

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Checking availability for your team

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Anthropic

Legal:Terms•Privacy

200K

64K

1.0 s

48 tps

$5/M

$25/M

Read$0.50/M

Write$6.25/M

$10/K

11/24/2025

Bedrock

Legal:Terms•Privacy

200K

64K

1.3 s

46 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

—

11/24/2025

Google Vertex AI

Legal:Terms•Privacy

200K

64K

0.7 s

47 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

11/24/2025

Getting started

Call Claude Opus 4.5 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Opus 4.5 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `anthropic/claude-opus-4.5`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Opus 4.5 supports up to `64,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 200K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK anthropic provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['anthropic', 'bedrock'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.5',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Anthropic

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

anthropic/claude-fable-5.1

1.1 s

82 tps

$10/M

$50/M

Read$0.25/M

Write$12.50/M

$10/K

08/31/2026

anthropic/claude-opus-5

2.5 s

117 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

07/24/2026

anthropic/claude-sonnet-5

1.6 s

119 tps

$2/M

$10/M

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

anthropic/claude-opus-4.8

0.8 s

107 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

05/28/2026

anthropic/claude-sonnet-4.6

0.7 s

61 tps

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

anthropic/claude-haiku-4.5

200K

0.5 s

101 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Copy link to headingAbout Claude Opus 4.5

Claude Opus 4.5 became available on AI Gateway on November 24, 2025. The model adds a new effort parameter that affects all token types and governs how much token usage the model applies per request. It defaults to high and operates independently of the thinking budget, giving you a separate lever for token efficiency without adjusting extended thinking configuration.

Difficult coding tasks and agentic workflows are core strengths, especially those combining computer use and tool use. Claude Opus 4.5 handles context from external memory files effectively. Frontend coding and design for real-world web applications are established strengths of this checkpoint.

To use Claude Opus 4.5, set the model to anthropic/claude-opus-4.5 and configure effort through providerOptions in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats. The effort setting is independent of the thinking budget. Set both separately to manage the cost-quality tradeoff for different request types in the same application.

Anthropic designed Claude Opus 4.5 for the demanding end of the agent capability spectrum: workflows involving computer use, external tool calls, memory file management, and frontend development where design quality and code correctness both apply.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: The effort parameter (high by default) affects all token types for a request. Set it in providerOptions.anthropic.effort to manage token usage per request when running mixed workloads with varying complexity.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Claude Opus 4.5

Best for

Agentic workflows combining computer use and tool use: A core strength for tasks requiring both capabilities in combination
Frontend coding and design: Production-quality output on complex UI development tasks for real-world web apps
Demanding reasoning and complex problem solving: The effort parameter (high by default) applies maximum token usage per request for hard analytical work
External memory file handling: The model manages context across long agentic sessions with memory file access
Effort-level control: Workloads mixing simple and complex requests benefit from per-request token usage management

Consider alternatives when

Fastest interactive response: Haiku 4.5 or Sonnet 4 variants suit low-latency use
Sonnet-level depth suffices: A Sonnet model handles tasks that don't require Opus-level reasoning at lower cost
1M token context window: Context size came to Opus models with version 4.6

Copy link to headingConclusion

Claude Opus 4.5 is built for the demanding intersection of agentic workflows: computer use, external tool calls, memory management, and frontend development. The effort parameter gives teams explicit cost control on top of the model's capabilities. For organizations pushing the complexity ceiling of what agents can handle autonomously, it's the right Opus checkpoint prior to 4.6.

Copy link to headingFrequently Asked Questions

What is the effort parameter in Claude Opus 4.5 and how does it work?
The effort parameter controls how much token usage the model applies when responding to a request. It defaults to high, affects all token types, and is set independently of the thinking budget via providerOptions.anthropic.effort in the AI SDK.
How do I configure the effort parameter through AI Gateway?
Under providerOptions.anthropic in your AI SDK v5 call, pass an effort level of low, medium, or high alongside the model string anthropic/claude-opus-4.5.
What agentic capabilities does Opus 4.5 excel at specifically?
Difficult coding tasks, agentic workflows combining computer use and tool use, and complex multi-step problem solving. The model handles tasks requiring sustained reasoning across long contexts and multi-turn interactions.
How does effort differ from the thinking budget?
They are independent parameters. The effort parameter controls overall token usage across all token types; the thinking budget specifically controls extended reasoning tokens. You can set both separately to tune the cost-quality tradeoff.
What vision improvements does Opus 4.5 include?
Opus 4.5 includes improvements in general intelligence and visual reasoning, handling image analysis, diagram interpretation, and document understanding with stronger accuracy than previous Opus versions.
Does Opus 4.5 support the 1M token context window?
No. The 1M token context window came to Opus models with Claude Opus 4.6.
Is Claude Opus 4.5 suitable for frontend web development work?
Yes, frontend coding and design for developing real-world web applications is specifically listed as an established strength of this model.

Claude Opus 4.5

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Anthropic

Copy link to headingAbout Claude Opus 4.5

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Opus 4.5

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions