The Orchestrator › Models › Anthropic

Anthropic: Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

Specifications

ProviderAnthropic
Model IDanthropic/claude-opus-5.5
Context window1M tokens (1,000,000)
Modalitiestext + image + file → text
TokenizerClaude
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-09-22
Tracked since2026-11-14
Popularity#4 by usage · peak 24.7% spend share in an OpenRouter category
ReasoningMandatory

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteranthropic/claude-opus-5.5$4.00$20.001M
batchOpenRouteranthropic/claude-opus-5.5:batch$2.00$10.001M
standardTrustedRouteranthropic/claude-opus-5.5$4.22$21.101M
standardVercel AI Gatewayanthropic/claude-opus-5.5$4.00$20.001M
fastVercel AI Gatewayanthropic/claude-opus-5.5:fast$8.00$40.001M
batchVercel AI Gatewayanthropic/claude-opus-5.5:batch$2.00$10.001M
standardCloudflareanthropic/claude-opus-5.5$4.00$20.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$4.00$20.00—
2026-11-14$4.00$20.001M
2026-11-14$4.22$21.101M
2026-11-14$4.00$20.001M

Capabilities

Vision (image input)File inputAgentic tool useStructured outputsReasoning (always on)1M+ 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