LiteLLMModels

Claude Haiku 4.5 API Pricing

As of October 10, 2026, Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens on Anthropic, with cache reads at $0.10 and cache writes at $1.25 per 1M tokens. Across 12 providers on LiteLLM, the input price ranges from $1.00 to $1.10. It has a 200,000-token context window and returns up to 64,000 tokens per response.

By AnthropicModel ID claude-haiku-4-5Prices updated Checked
Input
$1.00 / 1M tokens
Output
$5.00 / 1M tokens
Cache read
$0.10 / 1M tokens
Context window
200,000 tokens
Max output
64,000 tokens
Providers
12
Added to LiteLLM
October 2025

Claude Haiku 4.5 pricing by provider

23 listings across 12 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-4-5$1.00$5.00$0.10$1.25$0.50$2.50200K
Anthropicsnapshot 20251001claude-haiku-4-5-20251001$1.00$5.00$0.10$1.25$0.50$2.50200K
AIHubMixaihubmix/claude-haiku-4-5$1.10$5.50$0.11$1.375––200K
Amazon Bedrocksnapshot 20251001anthropic.claude-haiku-4-5-20251001-v1:0$1.00$5.00$0.10$1.25$0.50$2.50200K
Amazon Bedrockanthropic.claude-haiku-4-5@20251001$1.00$5.00$0.10$1.25––200K
Amazon Bedrock Mantlebedrock_mantle/anthropic.claude-haiku-4-5$1.00$5.00$0.10$1.25$0.50$2.50200K
Azure AI Foundryazure_ai/claude-haiku-4-5$1.00$5.00$0.10$1.25––200K
Databricksdatabricks/databricks-claude-haiku-4-5$1.00$5.00$0.10$1.25––200K
DeepInfradeepinfra/anthropic/claude-haiku-4-5$1.00$5.00––––200K
GitHub Copilotgithub_copilot/claude-haiku-4.5$1.00$5.00$0.10$1.25––128K
Google Vertex AIvertex_ai/claude-haiku-4-5$1.00$5.00$0.10$1.25$0.50$2.50200K
Google Vertex AIvertex_ai/claude-haiku-4-5@20251001$1.00$5.00$0.10$1.25$0.50$2.50200K
Perplexityperplexity/anthropic/claude-haiku-4-5$1.00$5.00$0.10––––
Snowflake Cortexsnowflake/claude-haiku-4-5$1.00$5.00$0.10–––200K
Vercel AI Gatewayvercel_ai_gateway/anthropic/claude-haiku-4.5$1.00$5.00$0.10$1.25––200K
Amazon BedrockAPAC cross-region, snapshot 20251001apac.anthropic.claude-haiku-4-5-20251001-v1:0$1.10$5.50$0.11$1.375$0.55$2.75200K
Amazon BedrockAustralia cross-region, snapshot 20251001au.anthropic.claude-haiku-4-5-20251001-v1:0$1.10$5.50$0.11$1.375$0.55$2.75200K
Amazon Bedrockus-gov-east-1, snapshot 20251001bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0$1.20$6.00$0.12$1.50––200K
Amazon Bedrockus-gov-west-1, snapshot 20251001bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0$1.20$6.00$0.12$1.50––200K
Amazon BedrockEU cross-region, snapshot 20251001eu.anthropic.claude-haiku-4-5-20251001-v1:0$1.10$5.50$0.11$1.375$0.55$2.75200K
Amazon BedrockGlobal cross-region, snapshot 20251001global.anthropic.claude-haiku-4-5-20251001-v1:0$1.00$5.00$0.10$1.25$0.50$2.50200K
Amazon BedrockJapan cross-region, snapshot 20251001jp.anthropic.claude-haiku-4-5-20251001-v1:0$1.10$5.50$0.11$1.375$0.55$2.75200K
Amazon BedrockUS cross-region, snapshot 20251001us.anthropic.claude-haiku-4-5-20251001-v1:0$1.10$5.50$0.11$1.375$0.55$2.75200K

Other Claude Haiku 4.5 prices on Anthropic

Cache write, 1 hour$2.00 per 1M tokens

What Claude Haiku 4.5 costs in practice

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

Anthropic$4.50
Amazon Bedrock$4.50
Amazon Bedrock Mantle$4.50
Azure AI Foundry$4.50
Anthropic batch$2.25

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

Anthropic$11.00
Amazon Bedrock$11.00
Amazon Bedrock Mantle$11.00
Azure AI Foundry$11.00

Claude Haiku 4.5 features

Use Claude Haiku 4.5 with LiteLLM

Call Claude Haiku 4.5 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-4-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: claude-haiku-4-5
    litellm_params:
      model: claude-haiku-4-5
      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-4-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Haiku 4.5 FAQ

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens on Anthropic, with cache reads at $0.10 and cache writes at $1.25 per 1M tokens. Batch requests cost $0.50 per 1M input tokens and $2.50 per 1M output tokens. Across 12 providers on LiteLLM, the input price ranges from $1.00 to $1.10.

What is the context window of Claude Haiku 4.5?

Claude Haiku 4.5 has a 200,000-token context window and returns up to 64,000 tokens per response.

Which providers offer Claude Haiku 4.5?

Claude Haiku 4.5 is available from 12 providers through LiteLLM: Anthropic, AIHubMix, Amazon Bedrock, Amazon Bedrock Mantle, Azure AI Foundry, Databricks, DeepInfra, GitHub Copilot, Google Vertex AI, Perplexity, Snowflake Cortex and Vercel AI Gateway. The lowest price is on Anthropic.

How do I call Claude Haiku 4.5 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="claude-haiku-4-5", 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 4.5 support?

Claude Haiku 4.5 supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching, web search and computer use.

When did LiteLLM add Claude Haiku 4.5?

Claude Haiku 4.5 was added to LiteLLM's model price file in October 2025.

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, AIHubMix, Amazon Bedrock, Azure AI Foundry, Databricks, DeepInfra.

Provider pages: Anthropic, AIHubMix, Amazon Bedrock, Amazon Bedrock Mantle, Azure AI Foundry, Databricks, DeepInfra, GitHub Copilot, Google Vertex AI, Perplexity, Snowflake Cortex, Vercel AI Gateway.