GPT-5.4 nano
openai/gpt-5-4-nanoОт OpenAI · семейство: gpt-nano · выпуск 2026-03-17 · дата знаний: 2025-08-31
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Возможности
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding92
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)12/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output87
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control0/10
- Price-friendly for high-volume17/20
Cost efficiency63
- Headline price (log-scaled)58/95
- Has prompt-cache pricing5/5
Long context70
- Context window (100K → 2M)60/90
- Has published price for full window10/10
Vision94
- Accepts image input50/50
- Context window (10K → 1M)24/30
- Has published price10/10
- Provider availability10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $1.63 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $3.25 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.03 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $2.85 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $3.15 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Детализация цен
Рекомендованная цена от openai · gpt-5.4-nano
Самый дешёвый провайдер: poe · $0.180 вход + $1.10 выход
Доступна у 14 провайдеров
| Провайдер | ID модели провайдера | Вход / 1M | Выход / 1M | Контекст | Выпуск |
|---|---|---|---|---|---|
| OpenAI openai | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| Azure Cognitive Services azure-cognitive-services | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| Azure azure | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| OpenRouter openrouter | openai/gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| Vercel AI Gateway vercel | openai/gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| 302.AI 302ai | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-19 |
| ZenMux zenmux | openai/gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-20 |
| Vivgrid vivgrid | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| Kilo Gateway kilo | openai/gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| OpenCode Zen opencode | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| Poe poe | openai/gpt-5.4-nano | $0.180 | $1.10 | 400K | 2026-03-11 |
| FrogBot frogbot | gpt-5-4-nano | $0.200 | $1.25 | 400K | 2025-08-07 |
| DigitalOcean digitalocean | openai-gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
| LLM Gateway llmgateway | gpt-5.4-nano | $0.200 | $1.25 | 400K | 2026-03-17 |
Расхождения данных между провайдерами
- release_date varies (span 225d): 2025-08-07, 2026-03-11, 2026-03-17, 2026-03-19, 2026-03-20
- modalities varies across offerings
Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.
Frequently asked questions
How much does GPT-5.4 nano cost?
GPT-5.4 nano costs $0.200 per 1M input tokens and $1.25 per 1M output tokens, sourced from openai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of GPT-5.4 nano?
GPT-5.4 nano has a context window of 400K tokens, with a max output of 128K tokens per reply. This is the total combined size of prompt + completion.
Does GPT-5.4 nano support tool calling?
Yes. GPT-5.4 nano supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does GPT-5.4 nano support structured output / JSON mode?
Yes. GPT-5.4 nano supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can GPT-5.4 nano accept image input?
Yes. GPT-5.4 nano accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check OpenAI's docs for the exact rule.
Is GPT-5.4 nano open-weight?
No. GPT-5.4 nano is a proprietary model — only OpenAI (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to GPT-5.4 nano?
If GPT-5.4 nano doesn't fit, consider GPT OSS 120B, GPT OSS 20B, GPT-5.2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More OpenAI models
- GPT OSS 120B$0.04 in / $0.16 out
- GPT OSS 20B$0.03 in / $0.14 out
- GPT-5.2$1.75 in / $14.00 out
- GPT-5 Mini$0.25 in / $2.00 out
- GPT-5$1.25 in / $10.00 out
Capability lists this model is in
Последнее обновление:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.