GPT-5.4 Nano
by OpenCode Zen · family gpt-nano · listed Mar 2026RTV
Compact GPT model for low-latency assistance and high-volume workloads
Current rates USD per 1M tokens
Input$0.20
Output$1.25
Cache read$0.02
Cache write—
Against the market
On the record
- Model id
gpt-5.4-nano- Context window
- 400K tokens
- Max output
- 128K tokens
- Input modalities
- text, image, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Aug 2025
- Released
- 2026-03-17
- Last updated
- 2026-03-17
- Provider docs
- opencode.ai/docs/zen
Back of the envelope
≈
Also listed at
- Poe$0.18 in · $1.10 out
- Vercel AI Gateway$0.20 in · $1.25 out
- 302.AI$0.20 in · $1.25 out
- Vivgrid$0.20 in · $1.25 out
- ZenMux$0.20 in · $1.25 out
- OpenAI$0.20 in · $1.25 out
- Merge Gateway$0.20 in · $1.25 out
- OrcaRouter$0.20 in · $1.25 out
- NEAR AI Cloud$0.20 in · $1.25 out
- LLM Gateway$0.20 in · $1.25 out
- Azure$0.20 in · $1.25 out
- Kilo Gateway$0.20 in · $1.25 out
- OpenRouter$0.20 in · $1.25 out
- FastRouter$0.20 in · $1.25 out
- Azure Cognitive Services$0.20 in · $1.25 out