LLM Reference

Nova Micro vs Trinity-Large-Preview

Nova Micro (2025) and Trinity-Large-Preview (2026) are compact production models from Amazon Web Services (AWS) AI and Arcee AI. Nova Micro ships a 128k-token context window, while Trinity-Large-Preview ships a 128k-token context window. On pricing, Nova Micro costs $0.04/1M input tokens versus $0.15/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Nova Micro is ~329% cheaper at $0.04/1M; pay for Trinity-Large-Preview only for provider fit.

Decision scorecard

Local evidence first
SignalNova MicroTrinity-Large-Preview
Best forprovider-routed productiontool-calling agents and provider-routed production
Decision fitRAG, Long context, and ClassificationRAG, Agents, and Long context
Context window128k128k
Cheapest output$0.14/1M tokens$0.45/1M tokens
Provider routes2 tracked3 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Nova Micro when...
  • Nova Micro has the lower cheapest tracked output price at $0.14/1M tokens.
  • Local decision data tags Nova Micro for RAG, Long context, and Classification.
Choose Trinity-Large-Preview when...
  • Trinity-Large-Preview has broader tracked provider coverage for fallback and route flexibility.
  • Trinity-Large-Preview uniquely exposes JSON / Tool use in local model data.
  • Local decision data tags Trinity-Large-Preview for RAG, Agents, and Long context.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Nova Micro

Nova Micro

$63.00

Cheapest tracked route/tier: OpenRouter

Trinity-Large-Preview

$233

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $170. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Nova Micro -> Trinity-Large-Preview
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Trinity-Large-Preview is $0.31/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Trinity-Large-Preview adds JSON / JSON / Tool use in local capability data.
Trinity-Large-Preview -> Nova Micro
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Nova Micro is $0.31/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for JSON / JSON / Tool use before moving production traffic.

Specs

Specification
Released2025-03-172026-01-27
Context window128k128k
Parameters400B
ArchitectureDecoder OnlyMixture of Experts
LicenseProprietaryApache 2.0OSI-approved
OpennessProprietaryOpen source
WeightsNot releasedAvailable
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: permitted
Knowledge cutoff--

Pricing and availability

Pricing attributeNova MicroTrinity-Large-Preview
Input price$0.04/1M tokens$0.15/1M tokens
Output price$0.14/1M tokens$0.45/1M tokens
Providers

Capabilities

CapabilityNova MicroTrinity-Large-Preview
VisionNoNo
MultimodalNoNo
ReasoningNoNo
JSON / Tool useNoYes
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.