Amazon · AI model
Amazon Nova Micro
Text-only first-generation Amazon Nova model with a 128K-token context window and up to 10K output tokens, priced at 0.035/0.14 USD per 1M input/output tokens on Amazon Bedrock.
Last verified Available 6 sources
Key specs
- Provider
- Amazon
- Family
- Amazon Nova
- API identifier
- amazon.nova-micro-v1:0
- Availability
- Available
- Release date
- 2024-12-03
- License
- Proprietary
- Context window
- 128,000 tokens
- Max output
- 10,000 tokens
- Knowledge cutoff
- October 2024
- API access
- Yes
- Consumer app
- Unknown
Capabilities
Inputs
- Text input Yes
- Image input No
- Audio input No
- Video input No
- File input No Nova v1 user guide lists document support as 'No' for Nova Micro
Outputs
- Text output Yes
- Image output No
- Audio output No
Features
- Reasoning Unknown
- Tool calling Yes Client-side tool calling
- Web search Unknown
"Unknown" means we have not verified this capability yet; it does not mean the model lacks it.
Pricing
Estimate your monthly cost →| Dimension | Tier | Price | Since | Verified | Source |
|---|---|---|---|---|---|
| Input tokens | base | $0.035 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; Standard tier, Geo cross-Region and in-Region inference. |
| Cached input tokens | base | $0.00875 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; cache read is 75% less than the on-demand input price (pricing page; 0.00875 also listed explicitly). |
| Output tokens | base | $0.14 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; Standard tier, Geo cross-Region and in-Region inference. |
| Batch input tokens | base | $0.0175 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; Batch price as listed on the pricing page (50% of on-demand). |
| Batch output tokens | base | $0.07 per 1M tokens | 2026-10-12 | 2026-10-25 | Amazon Bedrock Pricing US East (N. Virginia), on-demand list price; Batch price as listed on the pricing page (50% of on-demand). |
Prices are shown in the currency the provider publishes; we never convert currencies.
Benchmarks
| Benchmark | Setting | Score | Reported by | Measured | Verified | Source |
|---|---|---|---|---|---|---|
| Text Arena Arena score, higher is better | Overall; style control on (default view) | 1,241 | Third party | 2026-10-08 | 2026-10-12 | Text Arena leaderboard (Arena) |
Scores measure voter preference, which can be influenced by answer style and length. The leaderboard offers a style-control adjustment, so record which view was used. Scores shift with every update, so a value is only meaningful together with its leaderboard date. Entries marked "Preliminary" or with few votes have wide confidence intervals. The same model can appear several times with different reasoning-effort suffixes (for example -high or -max). Category views (Coding, Math, Creative Writing and others) are different rankings from Overall.
One row per result, without rank numbers: each result was measured under its own setting (effort level, harness, tools, test version), as stated by the source, and scores compare only within the same setting. Self-reported results come from the provider and have not been reproduced independently.
Rankings
- #36 of 42 in Best AI API as of 2026-10-26
Derived from our published ranking snapshots; each ranking explains its criteria and weights.
Compare Amazon Nova Micro
Guides
About Amazon Nova Micro
Nova Micro is the text-only model of the first Amazon Nova generation (model ID amazon.nova-micro-v1:0), announced as available in Amazon Bedrock on December 3, 2024; AWS positions it for speed and low cost in tasks such as summarization, translation and classification. It has a 128K-token context window, 10K max output tokens and an October 2024 knowledge cutoff according to the Bedrock model card. The model card lists it as Active, with client-side tool calling, guardrails and prompt caching on the Standard service tier.
Strengths and weaknesses
Strengths
- List price of 0.035/0.14 USD per 1M input/output tokens, below the other Nova models in this catalog
- Client-side tool calling and explicit prompt caching
- Fine-tuning supported; batch inference at half the on-demand price
Weaknesses
- Text-only: no image, video, audio or document input
- Smaller 128K-token context window and 10K max output tokens
- Only the Standard service tier is supported; structured outputs are not supported
Sources
Last verified Page updated 2026-10-13