qwen
GPT-5.4 Nano vs Qwen3.6 Plus
68.9 overall · $0.731 / 1M
// openai
GPT-5.4 Nano
openai/gpt-5.4-nano
reasoningtool callingfile inputimage inputprompt caching
GPT-5.4 Nano costs $0.200 per 1M input tokens and $1.25 per 1M output tokens with a 400K-token context window.
A reasoning, tool-calling model from openai, released Mar 17, 2026. On LiveBench it scores 69.6 overall — #45 of 55 benchmarked models — and ranks highest in mathematics (#24).
- Input / 1M
- $0.200
- Output / 1M
- $1.25
- Context
- 400K
- LiveBench overall
- 69.6 · #45
Specs and pricing
| Input price USD per 1M prompt tokens | $0.200 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $1.25 |
| Blended price 3:1 input:output — #135 cheapest of 343 listed models | $0.463 |
| Cached input read Blank means not priced separately — not free | $0.020 |
| Cache write | — |
| Context window | 400,000 tokens |
| Max output | 128,000 tokens |
| Input modalities | file, image, text |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | 2025-08-31 |
| Listed | Mar 17, 2026 |
Also listed as openai/gpt-5.4-nano:batch ($0.231 blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with GPT-5.4 Nano's rank among the 55 benchmarked models listed here. Run: gpt-5.4-nano-xhigh.
Language#55 of 55
62.5
$0.0283 measured per point
What GPT-5.4 Nano costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $135.04/mo |
| RAG assistant 8K in / 600 out × 100K requests | $163.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $159.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $284.75/mo |
| Bulk classification 500 in / 20 out × 5M requests | $535.00/mo |
Compare GPT-5.4 Nano with
The benchmarked models closest to it on overall score.
moonshotai
GPT-5.4 Nano vs Kimi K2.6
70.5 overall · $1.71 / 1M
moonshotai
GPT-5.4 Nano vs Kimi K2.7 Code
68.4 overall · $1.35 / 1M
x-ai
GPT-5.4 Nano vs SpaceXAI: Grok Build 0.1
67.8 overall · $1.25 / 1M
deepseek
GPT-5.4 Nano vs DeepSeek V4 Pro 0423
71.6 overall · $1.08 / 1M
z-ai
GPT-5.4 Nano vs GLM 5.3 Flash
71.6 overall · $0.237 / 1M
GPT-5.4 Nano FAQ
How much does GPT-5.4 Nano cost?
GPT-5.4 Nano lists at $0.200 per 1M input tokens and $1.25 per 1M output tokens, with cached input reads at $0.020 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $163.00 at list price.
What is the context window of GPT-5.4 Nano?
GPT-5.4 Nano accepts up to 400,000 tokens of context and can return up to 128,000 output tokens per response.
Does GPT-5.4 Nano support tool calling?
Yes — GPT-5.4 Nano supports tool (function) calling and exposes extended reasoning. It accepts file, image, text input.
How does GPT-5.4 Nano score on benchmarks?
On LiveBench release 2026-06-25 (run: gpt-5.4-nano-xhigh), GPT-5.4 Nano scores 69.6 overall, ranking #45 of 55 benchmarked models.
What is the API model ID for GPT-5.4 Nano?
On OpenRouter the model ID is "openai/gpt-5.4-nano". It was listed on Mar 17, 2026.
More from openai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.