Claude Opus 4.5 API

anthropic/claude-opus-4.5
200K tokens · 1000 input / 5000 output credits / 1M tokens

Claude Opus 4.5 Chat turns conversation text and image context into code, analysis, and detailed answers for demanding multi-step tasks. Its 200K-token context keeps related files and instructions together while system guidance and tools shape the response.

Claude Opus 4.5

Anthropic · chat-completions

Chat with Claude Opus 4.5

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 4.5

Claude Opus 4.5 accepts ordered conversation messages and returns text responses for complex coding and analysis. Its 200K-token context window can hold related documents, code, and prior turns, while image blocks provide visual evidence for focused questions. Choose /v1/chat/completions for an ordered messages array with a system role, or /v1/messages for a separate system field. Both endpoints return a complete JSON response by default.

Why Choose Claude Opus 4.5?

  • Connected coding workKeep requirements, source files, and test findings together while developing and reviewing a multi-step change.

  • Long-document reasoningCompare related passages, instructions, and evidence within a 200K-token context window.

  • Visual evidence in answersCombine a chart, diagram, or screenshot with a written question and get a grounded text explanation.

Parameters

/v1/chat/completions

ParameterRequirementDescription
modelRequired

Use anthropic/claude-opus-4.5.

messagesRequired

A non-empty ordered array of conversation messages; each item contains role and content.

max_tokensOptional

A positive integer setting the response output limit; the Playground offers 1?65,536.

Default4096
temperatureOptional

Sampling temperature; the Playground offers 0?2.

Default1
top_pOptional

Nucleus sampling probability; the Playground offers 0?1.

Default1
streamOptional

Set true for an SSE event stream; the Playground uses complete JSON responses.

Defaultfalse

/v1/messages

ParameterRequirementDescription
modelRequired

Use anthropic/claude-opus-4.5.

messagesRequired

A non-empty ordered array of conversation messages; each item contains role and content.

systemOptional

System instructions supplied separately from messages.

max_tokensRequired

A positive integer setting the response output limit; the Playground offers 1?65,536.

Default4096
temperatureOptional

Sampling temperature; the Playground offers 0?2.

Default1
top_pOptional

Nucleus sampling probability; the Playground offers 0?1.

Default1
streamOptional

Set true for an SSE event stream; the Playground uses complete JSON responses.

Defaultfalse

How to Use

  1. Choose the endpointSelect /v1/chat/completions or /v1/messages and set model to anthropic/claude-opus-4.5.

  2. Provide the conversationAdd ordered messages. Put system guidance in a system-role message for Chat Completions, or in the system field for Messages.

  3. Set the response lengthSet max_tokens to a positive integer for Messages, then send the request and review the response and token usage.

Pricing

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

UsageRateDetails
Input$4.00 · 1000 credits / 1M tokensTokens in the request.
Output$20.00 · 5000 credits / 1M tokensTokens generated in the response.

Best Use Cases

  • Complex code changesTrace requirements through several files and ask for an implementation or review plan.

  • Document analysisCompare lengthy specifications, reports, and supporting evidence in one conversation.

  • Diagram interpretationAsk focused questions about architecture diagrams or charts alongside written context.

Pro Tips

  • Put the goal, constraints, relevant files, and review criteria in the same conversation.
  • Pair an image block with a specific question about the details you need analyzed.
  • Review returned token usage and keep the next turn focused on missing evidence.

Usage Notes

  • Claude Opus 4.5 has a 200K-token context window and a 64K-token model output limit.
  • The Playground max_tokens control ranges from 1 to 65,536 and starts at 4,096.
  • Use anthropic/claude-opus-4.5 with /v1/chat/completions or /v1/messages.

Related Models

Claude Opus 4.5 API frequently asked questions

What is the Claude Opus 4.5 API?

Claude Opus 4.5 turns conversation text and image context into useful answers. Its 200K-token context supports connected work. Use anthropic/claude-opus-4.5 through Chat Completions or Claude Messages, or try the Playground above.

How does Claude Opus 4.5 help with complex coding?

Give Claude Opus 4.5 the target behavior, relevant source files, constraints, and test findings. It can connect those inputs to produce code and explain the decisions for review.

What context and output sizes does Claude Opus 4.5 have?

Claude Opus 4.5 has a 200K-token context window and a 64K-token model output limit. In the Playground, max_tokens ranges from 1 to 65,536.

How can Claude Opus 4.5 analyze images?

Place an image block in messages.content alongside the relevant text, then ask a focused question about the visual details. The response is text.

What does Claude Opus 4.5 cost on Vidgo AI?

Claude Opus 4.5 is $4.00 and 1000 credits per 1M input tokens, and $20.00 and 5000 credits per 1M output tokens. The Pricing section shows both rates.

Which API endpoints can I use for Claude Opus 4.5?

Use anthropic/claude-opus-4.5 with /v1/chat/completions or /v1/messages. Choose Chat Completions for system-role messages or Messages for a separate system field.