Post-Cutoff
Search For AI agents

AnthropicClaude 4 familyLegacyReasoning modelReleased 15 Oct 2025

Claude Haiku 4.5

Cheap, low-latency model for classification, extraction, sub-agents and high-volume chat.

Model idclaude-haiku-4-5-20251001

Price$1 in, $5 out per 1M tokens

Checked8 October 2026

Knows up to February 2025

2,030events after its cutoff

90 historic, 473 major. 623 days of news.

It launched on 15 October 2025, already missing 40 of them. Coverage before 2026 is thin (80 entries for 2025), so this count is a floor.

Five things it has never heard of

Its cutoff, February 2025, is before this chart starts: every mark here is news it has never seen.

How to call it

8 ways to use Claude Haiku 4.5, with the model id each provider expects.

Providers, model ids, endpoints and docs for Claude Haiku 4.5
ProviderModel idEndpointDocs
Anthropic API (Claude API) claude-haiku-4-5-20251001Alias claude-haiku-4-5 https://api.anthropic.com/v1/messages platform.claude.com
AWS Bedrock (Messages API / Mantle) anthropic.claude-haiku-4-5 platform.claude.com
AWS Bedrock (InvokeModel) anthropic.claude-haiku-4-5-20251001-v1:0 platform.claude.com
Google Cloud Vertex AI claude-haiku-4-5@20251001 platform.claude.com
Microsoft Foundry (Azure) claude-haiku-4-5 platform.claude.com
Claude Platform on AWS claude-haiku-4-5 platform.claude.com
OpenRouter anthropic/claude-haiku-4.5 openrouter.ai
Web app claude.ai

Pricing

Prices for Claude Haiku 4.5
Input$1 per 1M tokens
Output$5 per 1M tokens
Cache read$0.10 per 1M tokens

As published: “per 1M tokens (USD); Batch API 50% off”.

Source: platform.claude.com, checked 8 October 2026.

Specs

Input
Text, images and PDF
Output
Text
Context window
200,000 tokens
Max output
64,000 tokens
Open weights
No
Licence
Proprietary
Training cutoff
February 2025
Released
15 October 2025
Status
Legacy
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Sonnet-4-class coding at Haiku price

    73.3% on SWE-bench Verified, roughly matching Sonnet 4 at one-third the cost and over 2x the speed.

    Source: anthropic.com

  • Sub-agent workhorse

    Reaches about 90% of Sonnet 4.5 on Augment’s agentic eval; Anthropic positions it for multi-agent orchestration.

    Source: anthropic.com

  • Haiku with extended thinking and computer use

    First

    First Haiku model with extended thinking; it also surpasses Sonnet 4 on some computer-use tasks.

    Source: anthropic.com

Four assistants, one scale

Claude Haiku 4.5 is added as a fifth row. Each row runs from what the model knows (graphite) through the months between its cutoff and its launch (hatched) to today (pink).

  1. GPT-6 Astra 271 at launch, 1,863 today
  2. Claude Opus 5.5 372 at launch, 1,795 today
  3. Gemini 4 Hydrogen 1,863 at launch, 1,889 today
  4. Grok 4.7 387 at launch, 1,829 today
  5. Claude Haiku 4.5 40 at launch, 2,030 today
Show as a table
ModelCutoffReleasedMissing at launchMissing today
GPT-6 AstraApril 20263 September 20262711,863
Claude Opus 5.5June 202622 September 20263721,795
Gemini 4 HydrogenMarch 202612 November 20261,8631,889
Grok 4.7May 202621 September 20263871,829
Claude Haiku 4.5February 202515 October 2025402,030

Notes

Legacy since Claude Haiku 5.5 (Oct 7, 2026), which is 90% cheaper; still available. Snapshot claude-haiku-4-5-20251001 (alias claude-haiku-4-5). Uses extended thinking (thinking type enabled + budget_tokens), no effort parameter. Training data cutoff Jul 2025. Retirement not sooner than 2026-10-15. Batch $0.50/$2.50.

curl https://api.anthropic.com/v1/messages \
 -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -H "content-type: application/json" \
 -d '{"model":"claude-haiku-4-5","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'

Sources: