Side-by-side comparison
Nova Pro 1.0 vs Claude 3 Haiku
Anthropic
Claude 3 Haiku
👁 Vision
🔧 Tools
Input / 1M
$0.2500
Output / 1M
$1.2500
| Nova Pro 1.0 | Claude 3 Haiku | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 300,000 | 200,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools | vision, tools |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.8000 | 0.2500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 3.2000 | 1.2500 |
Frequently asked questions
Which is cheaper, Nova Pro 1.0 or Claude 3 Haiku?
Claude 3 Haiku is cheaper than Nova Pro 1.0 on a 50/50 input/output blend by about $1.25 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Nova Pro 1.0 or Claude 3 Haiku?
Nova Pro 1.0 has the larger context window at 300k tokens versus 200k tokens for Claude 3 Haiku. That means Nova Pro 1.0 can ingest about 1.5x as much text per request.
What is the difference between Nova Pro 1.0 and Claude 3 Haiku?
Nova Pro 1.0 comes from Amazon; Claude 3 Haiku comes from Anthropic. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.