Anthropic · Claude 4 5 · active
Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic's fastest current model with near-frontier intelligence.
anthropic/claude-haiku-4-5-20251001This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Provider availability
Serving endpoints and pricing
| Provider | Route model | Tier | Input | Output | Region | Observed | Source |
|---|---|---|---|---|---|---|---|
AnthropicRoute-ready | claude-haiku-4-5-20251001 | Standard | $1.00 | $5.00 | Unknown | Aug 28, 2026 | Provider-reported |
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Architecture
- Tokenizer
- Knowledge cutoff
Comparable peers
Related model comparisons
Questions
Claude Haiku 4.5 FAQs
What is Claude Haiku 4.5?+
Claude Haiku 4.5 is Anthropic's fastest current model with near-frontier intelligence. It is developed by Anthropic and its current sourced lifecycle status is active.
What inputs and outputs does Claude Haiku 4.5 support?+
Claude Haiku 4.5's current record lists Text and Image as input and Text as output.
How much context does Claude Haiku 4.5 support?+
The current record lists a 200,000-token context window and a maximum output of 64,000 tokens.
Is Claude Haiku 4.5 available through an API?+
Claude Haiku 4.5 is marked as API-available. The directly sourced provider records currently include Anthropic.
What capabilities and tasks does Claude Haiku 4.5 support?+
Claude Haiku 4.5's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are image and text.
Can Claude Haiku 4.5 be self-hosted?+
Claude Haiku 4.5 is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
Does Claude Haiku 4.5 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are claude-haiku-4-5-20251001.
Which models can Claude Haiku 4.5 be compared with?+
The current compatible peer set includes Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Qwen3.5-35B-A3B, and Ministral-3-14B-Reasoning-2512. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for Claude Haiku 4.5?+
Claude Haiku 4.5 was last verified Aug 28, 2026 from Anthropic's primary source, “Models overview | Claude Platform Docs.” The evidence is classified as official fact.
Primary evidence