GPT-5.4 Nano
OpenAI · Proprietary · Released Mar 17, 2026 · openai/gpt-5.4-nano
400K contextVisionToolsReasoningStructured outputPrompt caching
Available from 4 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 OpenAI1ST PARTY | $0.10 | $0.625 | $0.01 | 400K | — | 0.39s | 176 tok/s | 84.7% |
| OpenAI1ST PARTY | $0.20 | $1.25 | $0.02 | 400K | — | — | — | 84.7% |
 Azure | $0.20 | $1.25 | $0.02 | 400K | — | 1s | 85 tok/s | 100.0% |
| Azure | $0.22 | $1.38 | $0.022 | 400K | — | — | — | 96.4% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.10 / $0.625
per MTok in / out
BATCH
$0.05 / $0.313
async batch
CACHE READ $0.01WEB SEARCH $0.01 / search
About
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
Specifications
Context window400,000
Max output128,000
Modalities infile, image, text
Modalities outtext
LicenseProprietary
ReleasedMar 17, 2026
Knowledge cutoff2025-08-31
TokenizerGPT
Related
Embed badge
[](https://modelindex.ai/models/openai/gpt-5.4-nano)Sources
OpenRouter API4 minutes ago
AGGREGATORLiteLLM dataset4 minutes ago
AGGREGATORModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.