As of August 21, 2026, Nova Micro is 96% cheaper per million tokens than Nova Pro. Nova Micro is $0.03 / $0.14 per million input/output tokens versus Nova Pro at $0.80 / $3.20. Source: https://anotherwrapper.com/tools/llm-pricing
Source: AnotherWrapper LLM pricing (https://anotherwrapper.com/tools/llm-pricing)
Nova Micro
Amazon
Input
$0.03
Output
$0.14
Nova Pro
Amazon
Input
$0.80
Output
$3.20
Token pricing, specs, and benchmarks side by side
Nova MicroNova ProVerdict
Nova Micro offers significantly lower pricing, while Nova Pro leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 21, 2026, Nova Micro is 96% cheaper on blended LLM API pricing. Nova Micro costs $0.03 per million input tokens and $0.14 per million output tokens ($0.17 blended 1M-in + 1M-out). Nova Pro costs $0.80 / $3.20 per million tokens ($4.00 blended). Sources: https://anotherwrapper.com/tools/llm-pricing and https://anotherwrapper.com/tools/llm-pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
Nova Micro Amazon API pricing is $0.03 input and $0.14 output per million tokens via Amazon. Nova Pro Amazon API pricing is $0.80 input and $3.20 output per million tokens via Amazon. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Nova Pro leads on HumanEval: Nova Micro at 81.1% vs Nova Pro at 89%. SWE-bench measures real GitHub fixes; LiveCodeBench measures contest programming.
Nova Micro supports a 128K token context window, while Nova Pro supports 300K tokens. Nova Pro offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Nova Pro leads on 17 of 17 shared benchmarks versus Nova Micro's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Nova Micro and Nova Pro are production API models. For cost-sensitive production traffic, Nova Micro has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Nova Micro through Amazon and Nova Pro through Amazon with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Amazon API pricing and Amazon API pricing, quoted per million tokens. Official rate sheets: https://anotherwrapper.com/tools/llm-pricing and https://anotherwrapper.com/tools/llm-pricing. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Nova Micro supports up to 128K output tokens per request, while Nova Pro supports up to 300K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Nova Micro runs at approximately 100 tokens/second while Nova Pro runs at 100 tokens/second. Nova Pro is faster in raw throughput. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Nova Micro or Nova Pro from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Nova Micro costs $0.03/M input and $0.14/M output. Nova Pro costs $0.80/M input and $3.20/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
