Claude Opus 4.7 API

anthropic/claude-opus-4.7
1M tokens · 800 input / 4000 output credits / 1M tokens

Claude Opus 4.7 works across code, documents, and image context to produce detailed reasoning and reviewable answers. Its 1M-token context window and 128K-token maximum output support connected coding tasks through Chat Completions and Claude Messages.

Claude Opus 4.7

Anthropic · chat-completions

Chat with Claude Opus 4.7

Each model has its own conversation. Switching never sends another model's history, and switching back resumes where you left off. Requests are billed from actual token usage.

Ctrl / ⌘ + Enter to send0 / 32,000

Continue with

Claude Opus 4.7

Claude Opus 4.7 processes ordered conversation messages for coding, reasoning, and analysis. Its 1M-token context window can hold extensive source files and documents. Send anthropic/claude-opus-4.7 through /v1/chat/completions or /v1/messages. The Playground lets you switch API Endpoint and set System Prompt, Temperature, Max Tokens, and Top P.

Why Choose Claude Opus 4.7?

  • Connected coding workUse relevant source files, requirements, and tool results together to plan and review a multi-step code change.

  • Adjustable reasoning effortSet output_config.effort from low through max to match the depth of a coding or analysis task.

  • Long-context analysisCompare related code, documents, and conversation history within a 1M-token context window.

  • Text and image understandingPair image blocks with written context to examine charts, diagrams, and interface details.

Parameters

ParameterRequirementDescription
modelRequired

Set to anthropic/claude-opus-4.7.

messagesRequired

A non-empty ordered array of conversation messages; each message has role and content.

max_tokensMessages: required; Chat Completions: optional

A positive integer setting the response limit; the model API maximum is 128,000 output tokens.

systemOptional

Use a system role in messages for Chat Completions; send system at the root for Claude Messages.

temperatureOptional

Sampling temperature. The Playground uses 0–2 for Chat Completions and 0–1 for Claude Messages; default 1.

top_pOptional

Nucleus sampling probability from 0 to 1; default 1.

output_config.effortOptional

Claude Messages reasoning effort: low, medium, high, xhigh, or max.

Defaulthighlowmediumxhighmax
toolsOptional

Definitions of tools available during the response.

streamOptional

Choose a complete JSON response or an SSE event stream.

Defaultfalsetrue

How to Use

  1. Define the goalDescribe the deliverable, constraints, and criteria for review.

  2. Add contextProvide relevant files, conversation history, documents, or image blocks in messages.

  3. Set the requestChoose /v1/chat/completions or /v1/messages, send anthropic/claude-opus-4.7 in model, and set messages and Max Tokens.

  4. Review the responseInspect the generated content and reported token usage, then continue with new evidence as needed.

Pricing

Vidgo AI measures input and output tokens separately. Each rate below applies per 1M tokens.

UsageRateDetails
Input$4.00 · 800 credits / 1M tokensRequest input tokens.
Output$20.00 · 4000 credits / 1M tokensTokens generated in the response.

Best Use Cases

  • Repository-wide codingConnect implementation files, architecture constraints, and test output in one coding task.

  • Long-document analysisCompare requirements, reports, and source material to produce findings grounded in the supplied context.

  • Visual evidence reviewUse image blocks and focused questions to examine a chart, diagram, or interface.

Pro Tips

  • Provide the goal, constraints, relevant files, and acceptance criteria together.
  • Select output_config.effort to match the depth of reasoning the task needs.
  • Ask for findings tied to specific files or passages when reviewing extensive context.

Usage Notes

  • Claude Opus 4.7 has a 1,000,000-token context window and a 128,000-token maximum API output.
  • The Playground defaults to /v1/chat/completions and offers /v1/messages; its Max Tokens control spans 1–65,536.
  • Chat Completions places System Prompt in messages; Claude Messages sends system at the request root.

Related Models

Claude Opus 4.7 API frequently asked questions

What is the Claude Opus 4.7 API?

Claude Opus 4.7 is an Anthropic model for coding, reasoning, and long-context analysis. On Vidgo AI it accepts Chat Completions at /v1/chat/completions and Claude Messages at /v1/messages. Its 1M-token context window supports connected work across extensive source material.

How can Claude Opus 4.7 help with coding tasks?

Supply the target behavior, relevant files, constraints, and test results. The model can use that context to draft code, examine edge cases, and review the result against your criteria.

What is the Claude Opus 4.7 context window?

The context window is 1,000,000 tokens. Include the files, documents, and conversation turns needed to compare evidence across the task.

How do I set reasoning effort?

Set output_config.effort to low, medium, high, xhigh, or max in a Claude Messages request. The default is high.

What output limit applies to Claude Opus 4.7?

The model API supports up to 128,000 output tokens. Set max_tokens for each Claude Messages request. The on-page Playground offers a separate 1–65,536-token control.

How can Claude Opus 4.7 analyze images?

Place an image block alongside text in messages.content and ask a focused question about the visual details. The model returns a text response that uses the supplied image context.

How can I use tools with Claude Opus 4.7?

Define available tools in the request. When the model returns a tool call, your application executes it and sends the result in the next conversation turn.

What does Claude Opus 4.7 cost on Vidgo AI?

Input costs 800 credits ($4.00) per 1M tokens; output costs 4000 credits ($20.00) per 1M tokens. Use the reported token counts to calculate a request’s charge.