LiteLLMModels

Claude Haiku 5.5 API Pricing

As of October 10, 2026, Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens on Anthropic, with cache reads at $0.01 and cache writes at $0.125 per 1M tokens. Across 7 providers on LiteLLM, the input price ranges from $0.10 to $0.11. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

By AnthropicModel ID claude-haiku-5-5Prices updated Checked
Input
$0.10 / 1M tokens
Output
$0.50 / 1M tokens
Cache read
$0.01 / 1M tokens
Context window
1,000,000 tokens
Max output
128,000 tokens
Providers
7

Claude Haiku 5.5 pricing by provider

18 listings across 7 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeBatch inBatch outContext
Anthropicclaude-haiku-5-5$0.10$0.50$0.01$0.125$0.05$0.251M
Amazon Bedrockanthropic.claude-haiku-5-5$0.10$0.50$0.01$0.125––1M
Amazon Bedrock Mantlebedrock_mantle/anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Azure AI Foundryazure_ai/claude-haiku-5-5$0.10$0.50$0.01$0.125––1M
GitHub Copilotgithub_copilot/claude-haiku-5.5$0.10$0.50$0.01$0.125––128K
Google Vertex AIvertex_ai/claude-haiku-5-5$0.10$0.50$0.01$0.125$0.05$0.251M
Google Vertex AIvertex_ai/claude-haiku-5-5@default$0.10$0.50$0.01$0.125$0.05$0.251M
Perplexityperplexity/anthropic/claude-haiku-5-5$0.10$0.50$0.01––––
Amazon BedrockAPAC cross-regionapac.anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Amazon BedrockAustralia cross-regionau.anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Amazon Bedrockus-gov-east-1bedrock/us-gov-east-1/anthropic.claude-haiku-5-5$0.12$0.60$0.012$0.15––1M
Amazon Bedrockus-gov-west-1bedrock/us-gov-west-1/anthropic.claude-haiku-5-5$0.12$0.60$0.012$0.15––1M
Amazon BedrockEU cross-regioneu.anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Amazon BedrockGlobal cross-regionglobal.anthropic.claude-haiku-5-5$0.10$0.50$0.01$0.125––1M
Amazon BedrockJapan cross-regionjp.anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Amazon BedrockUS GovCloud cross-regionus-gov.anthropic.claude-haiku-5-5$0.12$0.60$0.012$0.15––1M
Amazon BedrockUS cross-regionus.anthropic.claude-haiku-5-5$0.11$0.55$0.011$0.1375––1M
Amazon Bedrock Mantleus-gov-west-1bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5$0.12$0.60$0.012$0.15––1M

Other Claude Haiku 5.5 prices on Anthropic

Cache write, 1 hour$0.20 per 1M tokens
Input above 100K tokens$0.50 per 1M tokens
Output above 100K tokens$2.50 per 1M tokens
Cache read above 100K tokens$0.05 per 1M tokens
Web search$10.00 per 1K searches

What Claude Haiku 5.5 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Anthropic$0.45
Amazon Bedrock$0.45
Azure AI Foundry$0.45
GitHub Copilot$0.45
Anthropic batch$0.225

100 long-document requests with 100,000 input and 2,000 output tokens each

Anthropic$1.10
Amazon Bedrock$1.10
Azure AI Foundry$1.10
GitHub Copilot$1.10

Claude Haiku 5.5 features

Use Claude Haiku 5.5 with LiteLLM

Call Claude Haiku 5.5 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="claude-haiku-5-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: claude-haiku-5-5
    litellm_params:
      model: claude-haiku-5-5
      api_key: os.environ/ANTHROPIC_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "claude-haiku-5-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Haiku 5.5 FAQ

How much does Claude Haiku 5.5 cost?

Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens on Anthropic, with cache reads at $0.01 and cache writes at $0.125 per 1M tokens. Batch requests cost $0.05 per 1M input tokens and $0.25 per 1M output tokens. Above 100K input tokens, input costs $0.50 and output costs $2.50 per 1M tokens. Across 7 providers on LiteLLM, the input price ranges from $0.10 to $0.11.

What is the context window of Claude Haiku 5.5?

Claude Haiku 5.5 has a 1,000,000-token context window and returns up to 128,000 tokens per response.

Which providers offer Claude Haiku 5.5?

Claude Haiku 5.5 is available from 7 providers through LiteLLM: Anthropic, Amazon Bedrock, Amazon Bedrock Mantle, Azure AI Foundry, GitHub Copilot, Google Vertex AI and Perplexity. The lowest price is on Anthropic.

How do I call Claude Haiku 5.5 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="claude-haiku-5-5", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Claude Haiku 5.5 support?

Claude Haiku 5.5 supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching, web search and computer use.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Anthropic, Amazon Bedrock, Azure AI Foundry, GitHub Copilot, Google Vertex AI, Perplexity.

Provider pages: Anthropic, Amazon Bedrock, Amazon Bedrock Mantle, Azure AI Foundry, GitHub Copilot, Google Vertex AI, Perplexity.