Log in
← All models

GPT-5.4

Balanced

The value flagship of the GPT-5 line — most of 5.5's ability for less than half the price.

OpenAI
Maker
90/100
Overall
46
Value score
$6.25
Blended /1M
1.1M
Context
Proprietary
Weights
Pricing: $2.50 in · $15 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality9.2/10 · 78% community
Agentic Ability9.1/10 · 78% community
Speed7.6/10 · 71% community
Value for $8.1/10 · 73% community
Reliability8.6/10 · 75% community

GPT-5.4 is the balanced GPT-5 model: most of the flagship's capability at roughly half the price and a bit faster. For day-to-day agent work it's the sweet spot in OpenAI's lineup, with the same 1M-token context as 5.5.

Strengths
  • Near-flagship quality for far less
  • 1M context
  • Reliable tool use
Trade-offs
  • A notch below 5.5 on the hardest tasks
  • Still pricier than open models

Agents that run GPT-5.4 well

The OpenAI daily driver — strong and well-priced.

Best model for CodexBest model for ClineBest model for AiderBest model for CursorBest model for ContinueBest model for OpenClaw

GPT-5.4 FAQ

Is GPT-5.4 good for AI agents?
The OpenAI daily driver — strong and well-priced. On our editorial scoring it rates 9.1/10 for agentic ability and 9.2/10 for output quality. Near-flagship quality for far less.
How much does GPT-5.4 cost?
Via OpenRouter, GPT-5.4 is priced at $2.50 in · $15 out / 1M tokens — a blended rate of about $6.25 per 1M tokens for typical input-heavy agent use.
What is GPT-5.4's context window?
GPT-5.4 has a 1.1M-token context window — large enough to hold sizeable codebases or document sets in a single run. OpenAI is the maker.
Can I self-host GPT-5.4?
No — GPT-5.4 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?
The main trade-offs: a notch below 5.5 on the hardest tasks; still pricier than open models. It's strongest for the openai daily driver — strong and well-priced.

GPT-5.4 compared

GPT-5.4 vs Sonnet 4.6GPT-5.4 vs Gemini 3.5 FlashGPT-5.4 vs GPT-5.3-CodexGPT-5.4 vs Kimi K2.7 CodeGPT-5.4 vs MiniMax M3GPT-5.4 vs Qwen3.7 PlusGPT-5.4 vs Devstral 2GPT-5.4 vs GLM 4.7

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 →