Log in
← All models

GPT-5.4 Mini

Budget

OpenAI's cheap, fast model for high-volume agent calls.

OpenAI
Maker
82/100
Overall
58
Value score
$1.88
Blended /1M
400K
Context
Proprietary
Weights
Pricing: $0.75 in · $4.50 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality8.0/10 · 72% community
Agentic Ability8.1/10 · 73% community
Speed9.0/10 · 77% community
Value for $8.2/10 · 74% community
Reliability8.7/10 · 76% community

GPT-5.4 Mini is the small, inexpensive GPT-5 model — fast, cheap, and good enough for the bulk of routine agent steps. A common choice for routing, classification, and the many small calls that would be wasteful on a flagship.

Strengths
  • Cheap and fast
  • 400K context
  • Solid instruction-following
Trade-offs
  • Not for hard reasoning or tricky refactors
  • Quality below the full GPT-5.4

Agents that run GPT-5.4 Mini well

High-volume, low-complexity agent steps on a budget.

Best model for CodexBest model for ClineBest model for ContinueBest model for OpenClawBest model for Hermes

GPT-5.4 Mini FAQ

Is GPT-5.4 Mini good for AI agents?
High-volume, low-complexity agent steps on a budget. On our editorial scoring it rates 8.1/10 for agentic ability and 8.0/10 for output quality. Cheap and fast.
How much does GPT-5.4 Mini cost?
Via OpenRouter, GPT-5.4 Mini is priced at $0.75 in · $4.50 out / 1M tokens — a blended rate of about $1.88 per 1M tokens for typical input-heavy agent use.
What is GPT-5.4 Mini's context window?
GPT-5.4 Mini has a 400K-token context window. OpenAI is the maker.
Can I self-host GPT-5.4 Mini?
No — GPT-5.4 Mini is a proprietary, hosted-only model from OpenAI. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of GPT-5.4 Mini?
The main trade-offs: not for hard reasoning or tricky refactors; quality below the full gpt-5.4. It's strongest for high-volume, low-complexity agent steps on a budget.

GPT-5.4 Mini compared

GPT-5.4 Mini vs Haiku 4.5GPT-5.4 Mini vs DeepSeek V4 FlashGPT-5.4 Mini vs Qwen3 235BGPT-5.4 Mini vs Flash LiteGPT-5.4 Mini vs Llama 4 MaverickGPT-5.4 Mini vs CodestralGPT-5.4 Mini vs GPT-5.5GPT-5.4 Mini vs GPT-5.4

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →