Claude/Fast / Budget

Claude Haiku 5.5

Claude Haiku 5.5 is Claude's fastest and most affordable model, priced at $0.10/MTok input and $0.50/MTok output with a 1M context window. Added by the model-onboarding job on 2026-10-08. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date from the provider model list. Not yet benchmarked, so never recommended.

Input $/MTok

$0.10

Output $/MTok

$0.50

Context window

1M

Cache read discount

90% off

Claude Haiku 5.5 pricing breakdown

RateInput $/MTokOutput $/MTok
Standard$0.10$0.50
Cached read (90% off input)$0.01-
Cached write (25% surcharge)$0.13-
Batch (50% off)$0.05$0.25
Long context (≥100.001K tokens)$0.50$2.50

All rates in USD per million tokens. Prices verified against provider documentation.

Claude Haiku 5.5 task benchmarks

Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 76 models.

Not benchmarked. The third-party benchmark source used for confidence scores does not cover Claude models yet. Scores will appear here once independent benchmarks are published.

Claude Haiku 5.5 cost by use case

Estimated cost per API call using default token counts for each workload.

Use caseInput tokensOutput tokensCost / call
Code Generation2,0004,000$0.002200
Unit Test Generation3,0005,000$0.002800
SQL Generation1,5001,000$0.000650
API Generation3,0006,000$0.003300
Code Refactoring4,0004,000$0.002400
Code Review5,0002,000$0.001500
PR Review8,0003,000$0.002300
Security Review6,0002,500$0.001850
Bug Detection5,0002,000$0.001500
Document Summarization10,0001,000$0.001500
PDF Summarization15,0001,500$0.002250
Meeting Notes8,0002,000$0.001800

Monthly cost projections

Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).

Calls / monthWithout cachingWith caching (90% read discount)
1K$2.2$2.07
10K$22$20.74
100K$220$207.4
500K$1,100$1,037
1M$2,200$2,074

Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.

Fast / Budget alternatives to Claude Haiku 5.5

Same-tier models from other providers, sorted by input price.

ModelProviderInput $/MTokOutput $/MTokInput savings
GPT 5 NanoGPT$0.05$0.4050% cheaper
GPT 4.1 NanoGPT$0.10$0.40Same price
GPT 6 LunaGPT$0.10$0.50Same price
Gemini 2.5 Flash-LiteGemini$0.10$0.40Same price
GPT 4o MiniGPT$0.15$0.6050% more
GPT 5.6 LunaGPT$0.20$1.20100% more
GPT 5.4 NanoGPT$0.20$1.25100% more
GPT 5 MiniGPT$0.25$2.00150% more
Gemini 3.1 Flash-LiteGemini$0.25$1.50150% more
Gemini 3.5 Flash-LiteGemini$0.30$2.50200% more
Gemini 2.5 FlashGemini$0.30$2.50200% more
GPT 4.1 MiniGPT$0.40$1.60300% more
GPT 3.5 TurboGPT$0.50$1.50400% more
GPT 3.5 Turbo (0125)GPT$0.50$1.50400% more
Gemini 3 FlashGemini$0.50$3.00400% more
GPT 5.4 MiniGPT$0.75$4.50650% more
Gemini 3.6 FlashGemini$0.75$3.75650% more
Gemini 3.7 FlashGemini$0.75$3.75650% more
Gemini 3.8 FlashGemini$0.75$3.75650% more
Gemini Robotics ER 2Gemini$1.00$5.00900% more
Grok Build 0.1Grok$1.00$2.00900% more
o3 MiniGPT$1.10$4.401000% more
o4 MiniGPT$1.10$4.401000% more
Gemini 2.5 Computer UseGemini$1.25$10.001150% more
Gemini 3.5 FlashGemini$1.50$9.001400% more
Gemini Omni 1.1 FlashGemini$1.50$9.001400% more
Gemini Omni FlashGemini$1.50$9.001400% more

Claude Haiku 5.5 pricing history

Input launched

$0.10/MTok at launch

Oct 7, 2026

View full Claude Haiku 5.5 pricing history

Track your Claude Haiku 5.5 spend

See exactly how much you spend on Claude Haiku 5.5 and where you can save. Two-line wrapper install, no API keys shared.