OpenAI

GPT 5.4 Nano

OpenAIToken-basedDynamic Pricing
Alias:gpt-5.4-nano
Create API Key

Compare gpt-5.4-nano API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagestreamingfunction_callingtoolsstructured_outputjson_modevisionweb_searchcachingreasoningcode_interpretercontext:400000
Starting price
View full pricing
Context
400K
Maximum input window
Max output
128K
Maximum tokens per response
Modalities
→
Knowledge cutoff
Aug 2025
Released
Mar 2026

Pricing by Supplier

OpenAI
-40%
Openai官方接口
Input/ 1M tokens
$0.12$0.2
Output/ 1M tokens
$0.75$1.25
Cache Read/ 1M tokens
$0.012$0.02
Azure
-40%
微软云API直连,稳定可靠
Input/ 1M tokens
$0.12$0.2
Output/ 1M tokens
$0.75$1.25
Cache Read/ 1M tokens
$0.012$0.02
GPT官+AZ 混合
-40%
适合生产环境,az 和官 key 混合渠道
Input/ 1M tokens
$0.12$0.2
Output/ 1M tokens
$0.75$1.25
Cache Read/ 1M tokens
$0.012$0.02
GPT特价
-90%
适合vibe coding自用,gpt pro 号池
Input/ 1M tokens
$0.02$0.2
Output/ 1M tokens
$0.125$1.25
Cache Read/ 1M tokens
$0.002$0.02

Capabilities / Supported modalities

StreamingFunction callingToolsStructured outputVisionWeb searchPrompt cachingReasoningCode interpreter
Input
Output

Provider & data privacy

Provider
OpenAIDocs
Tokenizer
o200k_base
License
Proprietary (commercial)Proprietary
Data retention30 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·GPT 5.4 Nano

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About GPT 5.4 Nano

把重复判断变成稳定流程

GPT-5.4 nano 适合规则明确、需要频繁执行的工作,例如给客服消息分配类别、从收据中提取字段、筛选产品评论、整理搜索候选,或为后续处理生成简短摘要。它的重点是速度与成本,适合作为业务流程前端的初筛和整理助手。

它接受文本与图片输入,可以把视觉内容纳入同一套处理规则。比如,从商品截图中识别标题与促销信息,再按给定规则生成标签;从票据图片中提取日期、币种和金额,并标出看不清的字段。对于图片里的细字或关键数字,建议让它返回对应原文,方便核验。

结构化输出使结果容易交给程序处理。设计请求时,先列出固定字段、枚举范围和缺失值规则,再给少量代表样例,通常比要求自由发挥更适合批量任务。函数调用也可以让它把已识别的需求转交给查询或处理工具,承担智能体中的单一步骤。

候选排序可以依据你提供的相关性、时效性或业务优先级进行,但这类判断应通过真实样本评估。遇到材料互相矛盾、需要长链推理或决策影响较大的情况,可以让它标记出来,交给更强模型或人工继续分析。清晰的升级条件比让每条输入都得到确定答案更实用。

常见配置问题

分类标签太多怎么办? 把类别定义和边界案例写清楚,保留“其他”或“待复核”,并检查相近类别的混淆情况。

能直接做搜索排序吗? 可以为已提供的候选进行语义判断与排序;候选检索、索引维护和业务规则仍需要你的系统完成。

Use cases and prompting

先定义字段,再提交内容

为重复任务提供固定规则,输出保持简短。

将这条售后消息分为退款、物流、质量、咨询或其他。
返回 JSON:category、order_id、summary、needs_review。
order_id 只提取原文中明确出现的编号,缺失写 null。
summary 不超过 30 字;同时涉及多个诉求或信息不足时 needs_review 为 true。
消息:{客户原文}

图片提取时增加“看不清写 null,不补全数字”。候选排序时说明排序标准,并要求返回候选原有 ID,避免系统无法匹配结果。用包含模糊输入与边界类别的样本检查准确率后,再投入大量调用。

API access

API documentation

Code samples

RequestPOST/v1/chat/completions
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Supported parameters

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Rate limits

SupplierRPMTPMRPD
AzureUnlimitedUnlimitedUnlimited
GPT官+AZ 混合UnlimitedUnlimitedUnlimited
GPT特价UnlimitedUnlimitedUnlimited
OpenAIUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about gpt-5.4-nano

What is gpt-5.4-nano?

Compare gpt-5.4-nano API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call gpt-5.4-nano?

Create an API key with access to gpt-5.4-nano, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is gpt-5.4-nano priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

What is the context window of gpt-5.4-nano?

The model catalog lists a context window of 400000 tokens. Check the selected endpoint for request limits.

What is the maximum output of gpt-5.4-nano?

The model catalog lists a maximum output of 128000 tokens. Your request settings may set a lower limit.

How should I evaluate gpt-5.4-nano for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.