Claude Sonnet 4 vs Nova Premier 1.0
Claude Sonnet 4
Nova Premier 1.0
| Claude Sonnet 4 | Nova Premier 1.0 | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary β | 1,000,000 | 1,000,000 |
| 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 β | 3.0000 | 2.5000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3β5Γ pricier than input. Glossary β | 15.0000 | 12.5000 |
Frequently asked questions
Which is cheaper, Claude Sonnet 4 or Nova Premier 1.0?
Nova Premier 1.0 is cheaper than Claude Sonnet 4 on a 50/50 input/output blend by about $1.5 per 1M tokens. Exact savings depend on your input-vs-output ratio β use the cost calculator on this page for a workload-specific estimate.
What is the difference between Claude Sonnet 4 and Nova Premier 1.0?
Claude Sonnet 4 comes from Anthropic; Nova Premier 1.0 comes from Amazon. They differ in pricing, context window, and supported capabilities β see the side-by-side table on this page for the exact figures, refreshed nightly.