"The best thing since OpenClaw" (Hermes Tutorial)
Model the creator switched Hermes to from the GPT-4o default for the initial test.
Smaller, lower-cost OpenAI language model in the GPT-5.4 family, offered through the OpenAI API and ChatGPT.
Updated EU status checked Last shown
GPT-5.4 mini at a glance
- What is GPT-5.4 mini?
- GPT-5.4 mini is a model from OpenAI. Smaller, lower-cost OpenAI language model in the GPT-5.4 family, offered through the OpenAI API and ChatGPT.
- Who makes GPT-5.4 mini?
- GPT-5.4 mini is made by OpenAI.
- Does GPT-5.4 mini work in the EU?
- Available in the EU. OpenAI publishes Europe Terms of Use for EEA residents (OpenAI Ireland Ltd), a GDPR-aligned DPA, and data residency for the API and ChatGPT business products. No model-specific EU restriction was found. Last verified 14 Nov 2026.
- How much does GPT-5.4 mini cost?
- API pricing. Billed per token via the OpenAI API; exact rates not given in the provided material. Licence: Proprietary.
- Where was GPT-5.4 mini shown?
- In 1 creator video by Matthew Berman. Most recently by Matthew Berman on 28 Jun 2026, at 1:24 in “"The best thing since OpenClaw" (Hermes Tutorial)”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
GPT-5.4 mini is a smaller variant in OpenAI's GPT-5.4 model family, positioned for lower-latency and lower-cost workloads than the full-size model. The provided material contains no official specification page for it, so details such as context window, benchmarks and exact release date are not confirmed here.
In the YouTube material provided, Matthew Berman switched the Hermes agent from its GPT-4o default to GPT-5.4 mini for an initial test. This suggests it is usable as a backend model for agent frameworks through the API.
It is accessed through OpenAI's platform and API, with documentation at platform.openai.com/docs. The weights are proprietary and not downloadable. Check OpenAI's pricing and model pages for current per-token rates and feature support.
Key features
- Smaller, lower-cost variant of the GPT-5.4 family
- Available through the OpenAI API
- Usable as a model backend for agent frameworks such as Hermes
- Proprietary hosted model; weights not released
1 moment
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
GP
GPT-5.4
Model · OpenAI
OpenAI frontier language model used for coding, reasoning and agentic tasks, available via ChatGPT and the API.
Available in EULanguage Models
Release date n/aAPI
GP
GPT-5.5
Model · OpenAI
OpenAI language model available through ChatGPT, Codex and the API, used for coding, review and general tasks.
Available in EULanguage Models
Release date n/aFreemium
GL
GPT-5.6 Luna
Model · OpenAI
OpenAI's lighter, lower-cost GPT-5.6 model variant, suited to routine tasks such as setup and scripting work.
Available in EULanguage Models
Release date n/aAPI
GP
GPT-6.1
Model · OpenAI
OpenAI language model in the GPT-6.1 family; the Soul Max variant is noted by reviewers for low token use per task.
Available in EULanguage Models
Release date n/a
GS
GPT-6 Sol
Model · OpenAI
OpenAI's mid-tier GPT-6 model, positioned below GPT-6 Astra and above Luna, priced at $2/$10 per million tokens.
Available in EULanguage Models
Release date n/aPaid
GS
GPT-5.6 Sol
Model · OpenAI
OpenAI's GPT-5.6 Sol frontier model, with an Ultrafast API tier on Cerebras reaching up to 750 output tokens per second.
Limited in EULanguage Models
Release date n/aAPI