Amazon: Nova Micro
Nova Micro is a language model from Amazon released on Dec 3, 2024. It reads text and writes text, with a 128K token context window and up to 10K tokens per reply.
Show moreShow less
It costs $0.035 per million input tokens and $0.14 per million output tokens. Cached input bills at $0.0088, 75% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
3 providers serve it, including Vercel AI Gateway, Amazon Bedrock and Eden AI.
- Modalities
- In / out price
- $0.035 / $0.14 per 1M
- Context
- 128K
- Max output
- 10K
- Released
- Dec 3, 2024
- Knowledge cutoff
- Oct 2024
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Nova Micro pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.035 / 1M tokens | |
|---|---|---|
| Output | $0.14 / 1M tokens | |
| Cached input (read) | $0.0088 / 1M tokens | 75% off input |
| Cache write | $0.035 / 1M tokens |
Nova Micro providers
3 providers serve it, including Vercel AI Gateway, Amazon Bedrock and Eden AI. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Vercel AI Gateway | $0.035 | $0.14 | $0.0088 | 128K | 10K |
| Amazon Bedrock | $0.037 | $0.148 | $0.0093 | 128K | 10K |
| Eden AI | $0.035 | $0.14 | $0.0088 | 128K | 10K |
What Nova Micro costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Nova Micro through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Temperature
temperature
Alternatives to Nova Micro
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 33K context
Reads text. Tool calling. Served by 2 providers.
by mistralaiMay 1, 2025$0.06/M input tokens$0.06/M output tokens2 providers
- 33K context
Reads text. Tool calling, structured output. Served by 5 providers.
by mistralaiJan 30, 2025$0.05/M input tokens$0.08/M output tokens5 providers
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 12 providers.
by qwenJul 15, 2026$0.03/M input tokens$0.13/M output tokens12 providers
- 16K context
Reads text. Tool calling.
by mistralaiJan 1, 2025$0.038/M input tokens$0.10/M output tokens
- 131K context
Reads text and images. Tool calling, structured output. Served by 7 providers.
by googleMar 12, 2025$0.04/M input tokens$0.08/M output tokens7 providers
- 128K context
Reads text. Tool calling, structured output. Served by 5 providers.
by cohereDec 2, 2024$0.0375/M input tokens$0.15/M output tokens5 providers
More from Amazon
Reads text, images, audio and video, writes text and images. Reasoning.
by amazonDec 2, 2025$0.30/M input tokens$2.50/M output tokens
- Index 14.2
Reads text, images, audio and video. Reasoning.
by amazonDec 2, 20251M context$1.25/M input tokens$10/M output tokens
- 1M context
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 3 providers.
by amazonDec 2, 2025$0.30/M input tokens$2.50/M output tokens3 providers
- Index 13.4
Reads text. Tool calling. Served by 3 providers.
by amazonDec 1, 20251M context$0.51/M input tokens$4.25/M output tokens3 providers
- 1M context
Reads text and images. Tool calling.
by amazonOct 31, 2025$2.50/M input tokens$12.50/M output tokens
- 300K context
Reads text. Tool calling, structured output. Served by 4 providers.
by amazonDec 5, 2024$0.0595/M input tokens$0.238/M output tokens4 providers
Nova Micro questions
How much does the Nova Micro API cost?
$0.035 per million input tokens and $0.14 per million output tokens, with cached input at $0.0088. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Nova Micro?
128,000 tokens of input, and it can write up to 10,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Nova Micro?
3 providers serve it, including Vercel AI Gateway, Amazon Bedrock and Eden AI. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Nova Micro support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Nova Micro open source?
No. Amazon serves it through an API only, so you cannot download the weights or host it yourself.
When was Nova Micro released?
Dec 3, 2024, with training data up to Oct 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Nova Micro?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting