The Orchestrator › Models › Anthropic
Anthropic: Claude Opus 5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
Specifications
| Provider | Anthropic |
| Model ID | anthropic/claude-opus-5 |
| Context window | 1M tokens (1,000,000) |
| Modalities | text + image + file → text |
| Tokenizer | Claude |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare |
| Released | 2026-07-24 |
| Tracked since | 2026-11-14 |
| Popularity | #27 by usage · peak 5.6% spend share in an OpenRouter category |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | anthropic/claude-opus-5 | $5.00 | $25.00 | 1M |
| batch | OpenRouter | anthropic/claude-opus-5:batch | $2.50 | $12.50 | 1M |
| standard | TrustedRouter | anthropic/claude-opus-5 | $5.28 | $26.38 | 1M |
| aws | TrustedRouter | anthropic/claude-opus-5:aws | $5.28 | $26.38 | 1M |
| standard | Vercel AI Gateway | anthropic/claude-opus-5 | $5.00 | $25.00 | 1M |
| fast | Vercel AI Gateway | anthropic/claude-opus-5:fast | $10.00 | $50.00 | 1M |
| batch | Vercel AI Gateway | anthropic/claude-opus-5:batch | $2.50 | $12.50 | 1M |
| standard | Cloudflare | anthropic/claude-opus-5 | $5.00 | $25.00 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $5.00 | $25.00 | — |
| 2026-11-14 | $5.00 | $25.00 | 1M |
| 2026-11-14 | $5.28 | $26.38 | 1M |
| 2026-11-14 | $5.00 | $25.00 | 1M |
Capabilities
Vision (image input)File inputAgentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools, verbosity