New Sign up free, 10 calls on us. Up to $1, no card needed.

GPT-5.4 Mini

Released 2026-03-16

chatVisionCodeTool callingReasoningPrompt caching

GPT-5.4 Mini is OpenAI's "strongest mini model yet for coding, computer use, and subagents," bringing the strengths of GPT-5.4 to a faster, more efficient tier.

Input
text image $0.75/M
Output
text $4.5/M
Cache read
$0.375/M
Context
400K
vs GPT-4o
~85% cheaper
Knowledge cutoff
2025-08

Benchmarks

Above average2 / 10
GPT-5.4 Mini other models measured peer average no peer scored higher
SWE-Bench Pro
54.4%
OSWorld-Verified
72.1%
GDPval-AA v2 Elo · 642-1861
1171
GPQA Diamond
88%
CharXiv (RQ) no tools
80.3%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google MiniMax Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$0.75/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$4.5/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.375/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

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
  • Positioned as the strongest mini model for coding, computer use, and subagents
  • 400k context / 128k max output

per OpenAI official docs ↗

Use GPT-5.4 Mini 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-mini",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About GPT-5.4 Mini

  • It offers a 400K-token context window, 128K max output tokens, image input, and full support for streaming, function calling, and structured outputs, at a fraction of the flagship's price.
  • OpenAI's release note frames it as bringing GPT-5.4-class capabilities to a faster, more efficient model for high-volume workloads, and names coding, computer use, and subagent orchestration as the workloads it was tuned for.
  • Crucially for agent builders, it keeps the flagship's complete tool list (function calling, web search, file search, tool search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, and MCP), which is the line that separates it from the cheaper nano tier.
  • Reasoning effort spans none, low, medium, high, and xhigh, defaulting to none, and compaction is supported for long sessions.
  • The documented input ceiling inside the 400K window is 272K tokens, and the knowledge cutoff is August 2025.
  • Chat Completions, Responses, and Batch are all available upstream, along with prompt caching and its discounted cached-input rate, and the shipping snapshot is dated March 2026.
  • Because its window stops at 400K it never crosses the long-context billing threshold that reprices the 1M-class models, so cost stays linear as prompts grow.
  • Requests to GPT-5.4 Mini on Synthorai go through the same OpenAI-compatible endpoint as any GPT model.

FAQ

Is the GPT-5.4 Mini API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.75/M input tokens, that credit alone covers roughly 166 requests of ~8K tokens against GPT-5.4 Mini.

What is GPT-5.4 Mini best at?

Strongest mini for coding and subagents; a fraction of the flagship's price; 400K context with 128K output. See the About section for the full picture from the vendor's own release notes.

How much does GPT-5.4 Mini cost?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.375/M.

Does GPT-5.4 Mini support prompt caching?

Yes, automatically: OpenAI-served prompts cache with no code changes. Cached input tokens bill at $0.375/M vs $0.75/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 Mini?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-5.4-mini", and you're done. One API key covers every model on the gateway.

What is GPT-5.4 Mini's knowledge cutoff?

GPT-5.4 Mini'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.

Get your API key Compare your cost →