Nova 2 Lite

openrouter/amazon/nova-2-lite-v1 · family nova · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideopdf.

$0.85Blended $/1M (3:1)

$0.3Input $/1M

$2.5Output $/1M

$2.801M in + 1M out

—Cache read $/1M

#2981 of 5,000Cheapest rank

Provider: OpenRouter (openrouter)
Context: 1,000,000 tokens
Max output: 65,535 tokens
Capabilities: toolsreasoningtextimagevideopdf

Same model, other providers

“Nova 2 Lite” is offered by 4 providers — cheapest-effective first. Nova is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nova	free	free	$0.00	1000k
OpenRouter (this)	$0.3	$2.5	$0.85	1000k
Vercel AI Gateway	$0.3	$2.5	$0.85	1000k
Amazon Bedrock	$0.33	$2.75	$0.94	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at OpenRouter and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"amazon/nova-2-lite-v1","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):