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.
import { streamText } from 'ai'
const result = streamText({ model: 'anthropic/claude-opus-4.7', prompt: 'Why is the sky blue?'})What To Consider When Choosing a Provider
Zero Data Retention
AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.Authentication
AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
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.
When to Use Claude Opus 4.7
Best For
Long-running asynchronous agents:
Multi-step workflows where
taskBudgetcaps cost on open-ended autonomous executionVisual 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
Conclusion
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.
FAQ
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.
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.
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.
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.
Yes, Zero Data Retention is available for this model. ZDR on AI Gateway applies to direct gateway requests; BYOK flows aren't covered. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Rates are listed on this page. They reflect the providers routing through AI Gateway and shift when providers update their pricing.
Set the model to anthropic/claude-opus-4.7 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats. AI Gateway handles authentication, retries, and failover across anthropic, bedrock, vertexAnthropic.
