Claude Haiku 4.5 vs Claude Haiku 5.5

As of October 21, 2026, Claude Haiku 4.5 costs 900% more per input token than Claude Haiku 5.5 ($1.00 vs $0.10 per 1M) and has a 200K-token context window versus 1M.

Prices from LiteLLM's price fileChecked October 21, 2026

Claude Haiku 4.5 vs Claude Haiku 5.5 side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of October 21, 2026.
	Claude Haiku 4.5	Claude Haiku 5.5
Input, per 1M tokens	$1.00	$0.10
Output, per 1M tokens	$5.00	$0.50
Cache read, per 1M tokens	$0.10	$0.01
Cache write, per 1M tokens	$1.25	$0.125
Context window	200,000 tokens	1,000,000 tokens
Max output	64,000 tokens	128,000 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	12	7
Price shown is from	Anthropic	Anthropic
Added to LiteLLM	October 2025	–

Cheapest provider for each

Claude Haiku 4.5: Anthropic at $1.00 input and $5.00 output per 1M tokens (claude-haiku-4-5)
Claude Haiku 5.5: Anthropic at $0.10 input and $0.50 output per 1M tokens (claude-haiku-5-5)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of October 9, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Claude Haiku 4.5	Claude Haiku 5.5
Overall
Epoch Capabilities Index	142.2	159.3
Reasoning and knowledge
GPQA Diamond	71.2% (32K)	89.6% (max)
ARC-AGI-2	4.0% (32K)	61.3% (xhigh)
SimpleQA Verified	13.2%	23.8% (max)
Math
OTIS Mock AIME 2024-2025	66.7% (32K)	98.9% (xhigh)

When to pick which

Pick Claude Haiku 5.5 for

Costs 90% less per input token: $0.10 vs $1.00 per 1M.
Larger context window: 1,000,000 vs 200,000 tokens.

From differences in the data above only; where the data is equal, no reason is given.

Call Claude Haiku 4.5 or Claude Haiku 5.5 with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Claude Haiku 4.5
response = completion(model="claude-haiku-4-5", messages=messages)

# Claude Haiku 5.5
response = completion(model="claude-haiku-5-5", messages=messages)

# Claude Haiku 4.5, falling back to Claude Haiku 5.5 if the call fails
response = completion(model="claude-haiku-4-5", messages=messages, fallbacks=["claude-haiku-5-5"])

FAQ

Which is cheaper, Claude Haiku 4.5 or Claude Haiku 5.5?

Claude Haiku 5.5 is cheaper at 3 input tokens per output token: $0.20 per 1M tokens blended ($0.10 input, $0.50 output), versus $2.00 ($1.00 and $5.00) for Claude Haiku 4.5, as of October 21, 2026.

Which has the larger context window, Claude Haiku 4.5 or Claude Haiku 5.5?

Claude Haiku 5.5 has the larger context window: 1,000,000 tokens, versus 200,000 for Claude Haiku 4.5.

Can I switch from Claude Haiku 4.5 to Claude Haiku 5.5 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-haiku-4-5" to "claude-haiku-5-5", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.