The Orchestrator › Models › Anthropic

Anthropic: Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Specifications

ProviderAnthropic
Model IDanthropic/claude-sonnet-4.5
Context window1M tokens (1,000,000)
Modalitiestext + image + file → text
TokenizerClaude
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2025-09-29
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningSupported

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteranthropic/claude-sonnet-4.5$3.00$15.001M
batchOpenRouteranthropic/claude-sonnet-4.5:batch$1.50$7.501M
standardTrustedRouteranthropic/claude-sonnet-4.5-20250929:coding$3.17$15.82200K
datedTrustedRouteranthropic/claude-sonnet-4.5-20250929$3.17$15.82200K
standardVercel AI Gatewayanthropic/claude-sonnet-4.5$3.00$15.001M
batchVercel AI Gatewayanthropic/claude-sonnet-4.5:batch$1.50$7.501M
standardCloudflareanthropic/claude-sonnet-4.5$3.00$15.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$3.00$15.00—
2026-11-14$3.00$15.001M
2026-11-14$3.17$15.82200K
2026-11-14$3.17$15.821M
2026-11-14$3.00$15.001M

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, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p