The Orchestrator › Models › Anthropic

Anthropic: Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

Specifications

ProviderAnthropic
Model IDanthropic/claude-haiku-5.5
Context window1M tokens (1,000,000)
Modalitiestext + image + file → text
TokenizerClaude
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway
Released2026-10-07
Tracked since2026-11-14
Popularity#31 by usage · peak 4.2% spend share in an OpenRouter category
ReasoningSupported

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteranthropic/claude-haiku-5.5$0.1$0.51M
batchOpenRouteranthropic/claude-haiku-5.5:batch$0.05$0.251M
standardTrustedRouteranthropic/claude-haiku-5.5$0.105$0.5281M
standardVercel AI Gatewayanthropic/claude-haiku-5.5$0.1$0.51M
batchVercel AI Gatewayanthropic/claude-haiku-5.5:batch$0.05$0.251M

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$0.1$0.51M
2026-11-14$0.105$0.5281M
2026-11-14$0.1$0.51M

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, tool_choice, tools, verbosity