Claude 3 Haiku
Anthropic · Active · available in 14 of 31 regions
- Context window
- 200K
- 200,000 tokens
- Max output
- —
- Input / 1M
- $0.250
- us-east-1
- Output / 1M
- —
What Claude 3 Haiku is good for
editorialClaude 3 Haiku offers a 200K-token context window with tool use, and is the cheapest option from this provider at $0.250 per 1M input tokens. Callable in 14 of 31 regions.
Suits
- Long documents. 200K tokens covers long documents and multi-file context without splitting them.
- Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
- Images. Accepts image input: screenshots, scanned documents, charts and UI captures.
- Cost. The cheapest Anthropic model here at $0.250 per 1M input tokens — the default choice for high-volume, low-difficulty work.
Think twice if
- Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Summarisation and extraction
High-volume, structured output from unstructured input. Usually the cheapest workload to run well.
- · Turning a million support tickets into a fixed schema of product, severity and root cause.
- · Pulling line items, totals and dates off scanned invoices into JSON.
- · Condensing every meeting transcript into decisions taken and owners assigned.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Cross-region inference profiles (3)
Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $0.250 | — | — | — | — | — | API |
| us-west-2 US West (Oregon) | $0.250 | — | — | — | — | — | API |
Region availability
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, Claude 3 Haiku can be served without the request leaving 8 of the 25 jurisdictions with a Bedrock region.
Claude 3 Haiku appears in
Common questions
- How much does Claude 3 Haiku cost on Amazon Bedrock?
- $0.250 per 1M input tokens and — per 1M output tokens in us-east-1.
- Which AWS regions support Claude 3 Haiku?
- 14 of 31 regions: us-east-1, us-east-2, us-west-2, ca-central-1, eu-west-1, eu-west-3, eu-central-1, eu-central-2, ap-northeast-1, ap-northeast-2, ap-south-1, ap-southeast-1, ap-southeast-2, sa-east-1. Regions marked profile-only need a cross-region inference profile ID such as apac.anthropic.claude-3-haiku-20240307-v1:0 rather than the bare model ID.
- What is the context window of Claude 3 Haiku?
- 200,000 tokens (200K).
- What is the model ID for Claude 3 Haiku on Bedrock?
- anthropic.claude-3-haiku-20240307-v1:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: apac.anthropic.claude-3-haiku-20240307-v1:0, eu.anthropic.claude-3-haiku-20240307-v1:0, us.anthropic.claude-3-haiku-20240307-v1:0.