VidgoAI

Claude Opus 5 API

anthropic/claude-opus-5
1M tokens · 400 input credits / 1M tokens

Claude Opus 5 converts conversation messages into detailed analysis, code, plans, and tool-oriented responses. Use it for demanding agentic coding, multi-step reasoning, and enterprise analysis, with access through both Chat Completions and the Claude Messages protocol.

Claude Opus 5

Anthropic · chat-completions

Chat with Claude Opus 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 Sonnet 5GPT 5.6 SolGPT 5.6 Terra

Claude Opus 5

Claude Opus 5 accepts an ordered, non-empty messages array and returns generated text plus usage in synchronous JSON or SSE. Supply complete constraints, evidence, tool boundaries, and verification requirements for broad work that spans several dependent steps.

Why Choose This?

  • Difficult multi-step workProvide complex constraints, evidence, and acceptance criteria for tasks that require sustained reasoning.

  • Agentic codingUse repository context and verification requirements to plan, implement, and review broad software changes.

  • Two compatible protocolsChoose Chat Completions for OpenAI-style clients or Claude Messages for Anthropic-compatible integrations.

Parameters

ParameterRequirementDescription
messagesRequired

A non-empty ordered conversation array; each message provides a role and text content.

max_tokensOptional

Sets the maximum number of tokens returned by Chat Completions and is required by Claude Messages.

streamOptional

Set false for synchronous JSON or true for an ordered SSE event stream.

Defaultfalsetrue

How to Use

  1. State the objective and constraintsDefine the expected outcome, non-negotiable rules, and failure conditions before asking for execution.

  2. Provide complete working evidenceInclude repository context, policies, reports, or prior decisions needed across the full task.

  3. Describe tools and checkpointsSpecify available actions, permission boundaries, review gates, and completion criteria for agent work.

  4. Inspect the proposed executionReview assumptions, code changes, and verification results before accepting a broad recommendation.

Pricing

Vidgo AI meters input, output, cache-read, and cache-write tokens separately, then settles their sum in credits. Rates below are per 1M tokens.

UsageRateDetails
Input tokens400 credits / 1M tokensInput usage that does not hit prompt cache.
Output tokens2000 credits / 1M tokensTokens generated by the model.
Cache read40 credits / 1M tokensInput tokens read from prompt cache.
Cache write500 credits / 1M tokensFive-minute cache write rate; one-hour cache writes cost 800 credits per 1M tokens.

Best Use Cases

  • Complex codebase migrationCombine architecture rules, source files, and compatibility constraints into an ordered migration and verification plan.

  • Enterprise evidence reviewTurn policies, reports, and operational constraints into findings, conflicts, risks, and decision options.

  • Tool-driven incident analysisUse logs, system context, and tool results to build a timeline, test hypotheses, and document follow-up actions.

Pro Tips

  • Define tool permissions and human review gates before asking Opus to plan a long-running agent workflow.
  • Request an explicit plan and verification strategy before broad code changes so hidden assumptions are visible early.
  • Keep repeated system instructions and reference context unchanged when you intend to reuse the prompt cache.

Notes

  • The context window is 1M tokens, and the maximum output is 128K tokens.
  • Claude Opus 5 supports both /v1/chat/completions and native /v1/messages; the Playground uses Chat Completions.
  • The minimum positive charge for a successful request is 0.001 credit; requests without valid output are not charged.
  • If a provider returns valid content without usage, the backend estimates token usage for settlement.

Related Models

Claude Sonnet 5Anthropic · 1M tokensClaude Sonnet 5 text generation API from 170 credits per 1M input tokens.
GPT 5.6 SolOpenAI · 1M tokensGPT 5.6 Sol text generation API from 280 credits per 1M input tokens.
GPT 5.6 TerraOpenAI · 1M tokensGPT 5.6 Terra text generation API from 112 credits per 1M input tokens.
GPT 5.6 LunaOpenAI · 1M tokensGPT 5.6 Luna text generation API from 11.2 credits per 1M input tokens.
Kimi K3Moonshot AI · 1,048,576 tokensKimi K3 text generation API from 456 credits per 1M input tokens.

Claude Opus 5 API — Frequently asked questions

What is the Claude Opus 5 API?

Claude Opus 5 is developed by Anthropic. It accepts ordered conversation messages and returns generated text plus usage through Vidgo AI.

How do I call the Claude Opus 5 API?

Use model claude-opus-5 with /v1/chat/completions for OpenAI-style clients or /v1/messages for Claude-compatible clients. Both protocols support direct JSON responses and SSE streaming.

How much does Claude Opus 5 cost?

Per 1M tokens, Vidgo charges 400 credits for input, 2000 for output, and 40 for cache reads. Cache writes cost 500 credits for the five-minute tier or 800 for the one-hour tier. The minimum positive charge for a successful request is 0.001 credit.

What inputs does Claude Opus 5 accept?

Both supported protocols accept a non-empty messages array with role and text content. Chat Completions accepts max_tokens optionally, while Claude Messages requires it.

Which Claude 5 model should I choose?

Choose Opus for demanding multi-step reasoning, broad agentic coding, and enterprise evidence review. Choose Sonnet for recurring production coding, tool workflows, and analysis at lower Vidgo token rates.