The Orchestrator › Models › Anthropic

Anthropic: Claude Opus 4.6

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Specifications

ProviderAnthropic
Model IDanthropic/claude-opus-4.6
Context window1M tokens (1,000,000)
Modalitiestext + image + file → text
TokenizerClaude
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-02-04
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningSupported

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteranthropic/claude-opus-4.6$5.00$25.001M
batchOpenRouteranthropic/claude-opus-4.6:batch$2.50$12.501M
standardTrustedRouteranthropic/claude-opus-4.6$5.28$26.381M
codingTrustedRouteranthropic/claude-opus-4.6:coding$5.28$26.381M
awsTrustedRouteranthropic/claude-opus-4.6:aws$5.28$26.381M
standardVercel AI Gatewayanthropic/claude-opus-4.6$5.00$25.001M
batchVercel AI Gatewayanthropic/claude-opus-4.6:batch$2.50$12.501M
standardCloudflareanthropic/claude-opus-4.6$5.00$25.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$5.00$25.00—
2026-11-14$5.00$25.001M
2026-11-14$5.28$26.381M
2026-11-14$5.00$25.001M

Capabilities

Vision (image input)File inputAgentic tool useStructured outputs1M+ 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, temperature, tool_choice, tools, top_k, top_p, verbosity