GPT-5.4 Nano is OpenAI's "cheapest GPT-5.4-class model for simple high-volume tasks," and its page names the work precisely: classification, data extraction, ranking, and sub-agents, where speed and cost matter most.
- Input
- text image $0.2/M
- Output
- text $1.25/M
- Cache read
- $0.1/M
- Context
- 400K
- vs GPT-4o
- ~96% cheaper
- Knowledge cutoff
- 2025-08
Price in context
Where the price sits among 60 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 400,000 |
|---|---|
| Max output (vendor spec) | 128,000 |
| Knowledge cutoff | 2025-08 |
Prompt caching
| How it caches | automatic |
|---|---|
| Min prefix | 1,024 |
| Lifetime | 5-10m, up to 1h |
Thinking
| Vendor control | reasoning.effort |
|---|---|
| Accepted values | none · low · medium · high · xhigh |
| Default | none applied when the request sets nothing |
| Can be turned off | Yes |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text + image → text |
|---|
- Cheapest GPT-5.4-class model, targeted at classification/extraction/ranking/subagents
- computer use and tool search not supported
Use GPT-5.4 Nano in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="gpt-5.4-nano",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "gpt-5.4-nano",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.4-nano",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "gpt-5.4-nano",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gpt-5.4-nano")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About GPT-5.4 Nano
- It keeps the family's 400K-token context window and 128K max output while trading peak reasoning depth for speed and cost efficiency, and supports streaming, function calling, and structured outputs with an August 2025 knowledge cutoff.
- Reasoning effort runs from none, the default, through low, medium, high, and xhigh, so more deliberation is available when a hard case warrants paying for it.
- The capability gap against GPT-5.4 Mini is specific and documented rather than vague: tool search and built-in computer use are absent from nano's tool list, while function calling, web search, file search, image generation, code interpreter, hosted shell, apply patch, skills, and MCP all remain.
- Prompt caching with its discounted cached-input rate, compaction, image input, and the Batch API are supported across Chat Completions and Responses, and the documented input ceiling within the window is 272K tokens.
- It shipped alongside GPT-5.4 Mini in March 2026 as a dated snapshot, so a pinned build stays reproducible.
- When budget per call is the binding constraint and the task is a well-defined transformation rather than open-ended reasoning, it is the family's high-volume option.
- Synthorai serves GPT-5.4 Nano over the standard OpenAI-compatible chat interface.
FAQ
Is the GPT-5.4 Nano API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.2/M input tokens, that credit alone covers roughly 625 requests of ~8K tokens against GPT-5.4 Nano.
What is GPT-5.4 Nano best at?
Cheapest model of its class; trades reasoning depth for speed and cost; keeps 400K context and 128K output. See the About section for the full picture from the vendor's own release notes.
How much does GPT-5.4 Nano cost?
GPT-5.4 Nano costs $0.2 per million input tokens and $1.25 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.1/M.
Does GPT-5.4 Nano support prompt caching?
Yes, automatically: OpenAI-served prompts cache with no code changes. Cached input tokens bill at $0.1/M vs $0.2/M uncached; prompts need a 1,024-token stable prefix to cache (TTL 5-10m, up to 1h). Prompt caching guide →
How do I get access to GPT-5.4 Nano?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-5.4-nano", and you're done. One API key covers every model on the gateway.
What is GPT-5.4 Nano's knowledge cutoff?
GPT-5.4 Nano's knowledge cutoff is 2025-08, per the vendor's official documentation (as of 2026-07-09).
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.