AnthropicUpdated 2h ago

Anthropic: Claude 3.5 Haiku API Pricing

Live token cost for Anthropic: Claude 3.5 Haiku from Anthropic. Use the figures below for budgeting, then tune your exact request mix in the interactive calculator. Prices refresh every 24 hours from OpenRouter.

Input
$0.800
/ 1M tokens
Output
$4.00
/ 1M tokens
Cached input
$0.080
/ 1M tokens

Capabilities

200K context8K max outputVisionPrompt cachingBatch API (50% off)

Anthropic: Claude 3.5 Haiku cost at scale

Estimated monthly cost across common production volumes. Assumes 30-day months and the request shapes shown.

TierRequests / dayIn / out tokens$ / month
Hobby1,000500 / 200$36.00
Startup10,0001,500 / 500$960.00
Growth100,0003,000 / 800$16,800.00
Enterprise1,000,0008,000 / 2,000$432,000.00
Enterprise (batch mode)1,000,0008,000 / 2,000$216,000.00
Open Anthropic: Claude 3.5 Haiku in interactive calculator →

Compare Anthropic: Claude 3.5 Haiku vs.

Frequently asked questions

How much does Anthropic: Claude 3.5 Haiku cost?

Anthropic: Claude 3.5 Haiku costs $0.80 per 1M input tokens and $4.00 per 1M output tokens, with cached input at $0.08 per 1M tokens. A typical 1,500-token in / 500-token out request costs $0.00320.

Does Anthropic: Claude 3.5 Haiku support cached input?

Yes. Anthropic: Claude 3.5 Haiku supports prompt caching at $0.08 per 1M cached input tokens. Reuse the same system prompt or context across requests to cut input cost dramatically.

What is the Anthropic: Claude 3.5 Haiku context window?

Anthropic: Claude 3.5 Haiku supports a context window of 200,000 tokens (200K). Max output per response is 8,192 tokens.

What is Anthropic: Claude 3.5 Haiku good for?

Anthropic: Claude 3.5 Haiku is a good fit for general-purpose LLM tasks via the Anthropic API — chat, code, writing, summarization. For other use cases, run your specific input/output mix through the interactive calculator to compare against alternative models.