All times Eastern (ET)Provider pages checked daily at

Migrating from claude-3-5-haiku-20241022 to claude-haiku-4-5-20251001

What changes when you move from claude-3-5-haiku-20241022 to claude-haiku-4-5-20251001: input price +25%, output price +25%.

Status
Retired
Shutdown
Feb 19, 2026
Time left
—
Status
Active
Shutdown
not before Oct 15, 2026
Time left
—

Prices

USD per 1M tokens, standard tier
Typeclaude-3-5-haiku-20241022claude-haiku-4-5-20251001Change
Input$0.80first seen October 1, 2026 · source$1.00first seen October 1, 2026 · source+25%
Cached input$0.08first seen October 1, 2026 · source$0.10first seen October 1, 2026 · source+25%
Output$4.00first seen October 1, 2026 · source$5.00first seen October 1, 2026 · source+25%

At 1M input and 250K output tokens a month: $1.80 on claude-3-5-haiku-20241022, $2.25 on claude-haiku-4-5-20251001 (+25%).

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens
Limitclaude-3-5-haiku-20241022claude-haiku-4-5-20251001Change
Context windowNot published200,000 tokensin place when tracking began (October 6, 2026) · source—
Max output tokensNot published64,000 tokensin place when tracking began (October 6, 2026) · source—

Benchmarks

Same benchmark and source on both sides; settings named where they differ
Benchmarkclaude-3-5-haiku-20241022claude-haiku-4-5-20251001Change
Arena TextArena. Ranges don't overlap.1325 ±31414 ±2+89
Arena Text: CodingArena. Ranges don't overlap.1386 ±61481 ±4+95
GPQA DiamondEpoch AI, 32k (vs no setting).
Other settings
  • 38.1% → 60.5%
38.1%71.2%+33.1 pts
MATH Level 5Epoch AI, 32k (vs no setting).
Other settings
  • 46.4% → 86.9%
46.4%96.4%+50.0 pts
OTIS Mock AIME 2024-2025Epoch AI, 32k (vs no setting).
Other settings
  • 4.3% → 35.8%
4.3%66.7%+62.4 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for claude-3-5-haiku-20241022: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Not published for claude-haiku-4-5-20251001: Structured outputs, Function calling, PDF input, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs.

No aliases point at claude-3-5-haiku-20241022.

Aliases pointing at claude-haiku-4-5-20251001: claude-haiku-4-5 (in place when tracking began (October 6, 2026) · source)

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
claude-3-5-haiku-20241022Google Cloud Vertex AIclaude-3-5-haikuJul 5, 2026Retired on July 5, 2026
claude-haiku-4-5-20251001Amazon Bedrockanthropic.claude-haiku-4-5not before Oct 16, 2026Active
claude-haiku-4-5-20251001Microsoft Foundryversion 1claude-haiku-4-5Nov 15, 2026Active31 days
claude-haiku-4-5-20251001Microsoft Foundryversion 2claude-haiku-4-5Nov 15, 2026Active31 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

  1. Change the model string from claude-3-5-haiku-20241022 to claude-haiku-4-5-20251001.
  2. Re-check costs: claude-haiku-4-5-20251001 costs more than claude-3-5-haiku-20241022 (input +25%, output +25%).

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: claude-3-5-haiku-20241022, claude-haiku-4-5-20251001.