Skip to content
Uvilo OS
published Visibility internal Owner erik@uvilo.com Approver _ Created _ Updated _

gpt-5.4-nano

PropertyValue
Modelgpt-5.4-nano
ProviderOpenAI
Context windowNot listed in available documentation
Cost per 1M tokens (input / output)$0.20 / $1.25 (USD)

Pricing sourced from the OpenClaw Model Landscape reference (verified 2026-04-08). Re-verify against OpenAI pricing docs if reading more than 60 days after that date.

Strengths

  • Cheapest model in the GPT-5.4 family — ideal for high-volume, low-latency work
  • Fast; suitable for edge/embedded and bulk classification tasks

Quirks

  • Requires max_completion_tokens >= 300. Setting it to 150 causes finish_reason=length with empty content.
  • Does NOT accept the temperature parameter. Omit it entirely; passing it causes an error.

Quirks sourced from Forge/Forge_Infrastructure.md, Forge/Skills/Reindex_Typesense/SKILL.md, and Forge/Skills/Typesense_MCP/SKILL.md.

  • forge-indexing — indexing/embedding generation (heading-based chunking)
  • Lightweight classification
  • forge-router (light)