How much does Claude Haiku 5.5 cost?

Claude Haiku 5.5 costs $0.1 per 1 million input tokens and $0.5 per 1 million output tokens. This pricing is set by Anthropic.

What tokenizer does Claude Haiku 5.5 use?

Claude Haiku 5.5 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.

What is Claude Haiku 5.5's context window?

Claude Haiku 5.5 supports a context window of 1.0M tokens (1,000,000 tokens). The maximum output length is 128K tokens.

How does Claude Haiku 5.5 compare to other models?

You can compare Claude Haiku 5.5's pricing and capabilities against other LLMs in the comparison table above, or visit the full pricing page for a side-by-side view of all models.

How do I count tokens for Claude Haiku 5.5?

Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Claude Haiku 5.5 using the cl100k_base tokenizer.

Claude Haiku 5.5

Last verified October 9, 2026 · Anthropic pricing ↗

$0.100/1M input · $0.500/1M output · 1.0M context · Anthropic

Count Tokens

Tokens

—

Input Cost

—

Output Cost

—

Tokens

—

Input Cost

—

Output Cost

Estimate Monthly Cost

Monthly Cost Estimator

Quick:

API calls / dayAvg input tokens / callAvg output tokens / call

<$0.0001/mo

Pick a preset above or enter custom usage

Alternatives to Claude Haiku 5.5

Cheaper Alternative

GPT-4.1 Nano

$0.100 in · $0.400 out · OpenAI

17% cheaper with same or larger context

Premium Upgrade

Qwen3.8 Flash

$0.150 in · $0.470 out · Alibaba

Upgrade with 131K max output

Same Provider

Claude Haiku 4.5

$1.00 in · $5.00 out · Anthropic

Higher tier in Anthropic ecosystem

Pricing Details

AnthropicLaunched October 7, 2026. Two-tier card keyed on prompt length. Prompts up to 100,000 tokens: $0.10 input, $0.125 5-minute cache write, $0.20 1-hour cache write, $0.01 cache read (0.1x, not the 0.05x of Opus/Sonnet 5.5), $0.50 output; Batch $0.05/$0.25. LONG CONTEXT: over 100,000 prompt tokens (all input counted, cache reads and writes included) the WHOLE request bills $0.50 input / $0.625 / $1.00 cache writes / $0.05 cache read / $2.50 output; Batch $0.25/$1.25. Only Claude 4.6+ model without flat 1M pricing. No Fast mode. inference_geo 'us' 1.1x. Same short-prompt card as GPT-6 Luna ($0.10/$0.01/$0.125/$0.50), but Luna's long tier starts at 272K and only goes to $0.20/$0.75. 90% under Haiku 4.5 ($1/$5) below 100K, 50% above; Anthropic estimates ~75% lower cost on typical workloads. Newer tokenizer: ~30% more tokens than Haiku 4.5 for the same text. Context 1M, max output 128K (300K on Batch with output-300k-2026-03-24 beta). Adaptive thinking on by default, default effort medium (low/medium/high/xhigh/max); thinking can be disabled at high or below; budget_tokens, assistant prefill and non-default temperature/top_p/top_k error. Knowledge cutoff June 2026. Anthropic-reported: GDPval-AA v2.1 1620, OSWorld 2.1 72.4%, Terminal-Bench 4.0 39.2%, FrontierCode 1.1 46.4%, HLE 45.9%/57.4% with tools. Artificial Analysis Intelligence Index (max): 43 vs GPT-6 Luna 38, ~162K output tokens per task (~3x Luna), ~240 tok/s; provisional $0.21 per task vs Luna $0.07 (AA notes it excludes the >100K step-up). Luna leads on AA-Omniscience accuracy (44% vs 36%). Available on Claude API, Bedrock (anthropic.claude-haiku-5-5), Google Cloud, Microsoft Foundry, Claude Platform on AWS. Retirement not sooner than October 7, 2027. API ID: claude-haiku-5-5.

Input / 1M tokens

$0.1

Output / 1M tokens

$0.5

Context Window

1.0M

Max Output

128K

Full Pricing Table Token Calculator

Price History

Launched at current price on 2026-10-07. No price changes recorded since.

Frequently Asked Questions

Common questions about Claude Haiku 5.5 pricing and usage