What does the `taskBudget` parameter do?

It sets a token limit for an individual agentic turn, capping the maximum compute the model can use on open-ended autonomous work. Use it to bound runaway cost on long-running agents.

How is the `xhigh` effort level different from `high`?

`xhigh` sits between `high` and `max`, offering deeper adaptive thinking than `high` without going to the `max` ceiling. Use it when the task warrants more depth than `high` provides but `max` would be overkill.

Why don't I see reasoning traces in my responses?

Thinking content is omitted by default in Claude Opus 4.7. Configure the thinking display option (for example, `'summarized'`) when you want reasoning visible in the response.

Does AI Gateway support Zero Data Retention for Claude Opus 4.7?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

What is the pricing for Claude Opus 4.7?

Rates are listed on this page. They reflect the providers routing through AI Gateway and shift when providers update their pricing.

Anthropic

Claude Opus 4.7

Claude Opus 4.7 extends the Opus line with task budgets, an xhigh effort level, and stronger visual verification. It targets long-running asynchronous agents, multi-step knowledge work, and workflows requiring pixel-level chart transcription and high-resolution image handling.

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-4.7',
  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 4.7 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 4.7

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.

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

128K

1.3 s

55 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

04/16/2026

Bedrock

Legal:Terms•Privacy

128K

0.9 s

60 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

04/16/2026

Google Vertex AI

Legal:Terms•Privacy

128K

1.1 s

94 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

04/16/2026

Getting started

Call Claude Opus 4.7 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-4.7',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Opus 4.7 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-4.7',
    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-4.7`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Opus 4.7 supports up to `128,000` 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 1M-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-4.7',
    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-4.7',
    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-4.7',
    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-4.7',
    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-4.7',
    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-opus-5

1.7 s

90 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

1.4 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

1.1 s

104 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

1.0 s

67 tps

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

anthropic/claude-opus-4.6

1.2 s

54 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

02/05/2026

anthropic/claude-haiku-4.5

200K

0.5 s

115 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Copy link to headingAbout Claude Opus 4.7

Claude Opus 4.7 launched on AI Gateway on April 16, 2026. The model is optimized for long-running, asynchronous agents that execute complex, multi-step tasks. Over the 4.6 baseline, it strengthens knowledge-worker capabilities where visual verification of outputs matters and improves programmatic tool-calling with image-processing libraries.

Two API additions define the release. First, taskBudget lets you set token limits that cap individual agentic turns, bounding runaway cost on open-ended autonomous work. Second, adaptive thinking gains an xhigh effort level that sits between high and the max ceiling, giving finer-grained control over how deeply the model reasons. Thinking content is no longer returned by default; configure the display option when you want to surface it.

Claude Opus 4.7 handles pixel-level data transcription from charts and figures, high-resolution images for computer use and screenshot analysis, and document parsing where detail accuracy matters. Structured memory across conversation turns keeps state reliable over extended sessions.

Through AI Gateway, Claude Opus 4.7 is available with the standard unified API, observability, and provider routing. Set the model to anthropic/claude-opus-4.7 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Thinking content is omitted from responses by default in Claude Opus 4.7. Configure the thinking display option explicitly when you want reasoning traces surfaced in the response.
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 4.7

Best for

Long-running asynchronous agents: Multi-step workflows where taskBudget caps cost on open-ended autonomous execution
Visual verification tasks: Knowledge work that requires pixel-level transcription from charts, figures, and technical diagrams
Computer use at high resolution: Screenshot analysis, GUI automation, and document processing where image detail affects accuracy
Programmatic tool-calling with images: Agents that invoke image-processing libraries as part of multi-step reasoning
Extended agent sessions: Structured memory across turns keeps state reliable across long conversations

Consider alternatives when

Cost-sensitive production workloads: Claude Sonnet 4.6 provides Opus-approaching intelligence at Sonnet pricing for high-volume traffic
Interactive low-latency use cases: Claude Haiku 4.5 delivers faster responses for well-bounded high-throughput requests
Fixed thinking budget control: Claude Opus 4.6 accepts fixed thinking budgets when you need deterministic compute per request rather than adaptive scaling

Copy link to headingConclusion

Claude Opus 4.7 targets the hardest agentic workloads where tasks run for extended periods, span many steps, and involve visual verification. Task budgets, xhigh effort, and stronger image tool-calling make it a practical fit for knowledge-worker pipelines that previously pushed against Opus 4.6's limits.

Copy link to headingFrequently Asked Questions

What does the taskBudget parameter do?
It sets a token limit for an individual agentic turn, capping the maximum compute the model can use on open-ended autonomous work. Use it to bound runaway cost on long-running agents.
How is the xhigh effort level different from high?
xhigh sits between high and max, offering deeper adaptive thinking than high without going to the max ceiling. Use it when the task warrants more depth than high provides but max would be overkill.
Why don't I see reasoning traces in my responses?
Thinking content is omitted by default in Claude Opus 4.7. Configure the thinking display option (for example, 'summarized') when you want reasoning visible in the response.
What makes Claude Opus 4.7 better for image-heavy agents?
High-resolution image support for computer use, screenshots, and documents, plus stronger programmatic tool-calling with image-processing libraries. The model also transcribes pixel-level data from charts and figures with higher fidelity.
Does AI Gateway support Zero Data Retention for Claude Opus 4.7?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
What is the pricing for Claude Opus 4.7?
Rates are listed on this page. They reflect the providers routing through AI Gateway and shift when providers update their pricing.
How do I call Claude Opus 4.7 through AI Gateway?
Set the model to anthropic/claude-opus-4.7 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. AI Gateway handles authentication, retries, and failover across anthropic, bedrock, vertex.

Your use is subject to Anthropic's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Claude Opus 4.7

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 4.7

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Opus 4.7

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions