Amazon · Small and fast

Amazon Nova 2 Lite API pricing and specs

Amazon's small Nova model on Bedrock, with tool use and text, image and video input.

Input

⁨$0.30⁩

Cached input

—

Output

⁨$2.50⁩

US dollars per million tokens, standard tier, short-prompt rate

We could not read this price on the vendor's own pricing page. The figures come from third-party price trackers, so confirm them in your console before you budget.

This is the global cross-region price; single-region inference costs about 1.75 times as much.

Spec sheet

API model string: —
Provider: Amazon
Context: 1M tokens
Max output: 64K tokens
Released: December 2, 2025
Batch API: No batch discount listed
Documented agent features: Tool callingImage input

What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

Workload	Per task	Per 1,000 tasks
Support bot 4 calls, short tool lookups	⁨$0.016⁩	⁨$16⁩
Coding agent 30 calls, files and test output	⁨$1.10⁩	⁨$1,098⁩
Browser agent 25 calls, screenshots and page text	⁨$0.445⁩	⁨$445⁩
Research agent 15 calls, long search results	⁨$0.353⁩	⁨$353⁩