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

GPT-5.4 Released 2026-03-05

OpenAI chat vision code tools reasoning
Input$2.5/M
Output$15/M
Cache read$1.25/M
Context922K
vs GPT-4o~50% cheaper
Knowledge cutoff2025-08

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$1.625/M. Automatic prefix caching once a prompt passes the minimum length, with no code changes; cached reads are discounted (up to 90% on current models) and there is no write fee. 1.05M-token context / 128k max output; prompts over 272k input tokens billed at 2x input / 1.5x output; reasoning effort none-xhigh.

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

About GPT-5.4

1,050,000-token context window
More affordable flagship-class option
Full hosted tool set including web search

GPT-5.4 is OpenAI's frontier model for coding and professional work, positioned as the more affordable flagship-class option.

  • It expands the family to a 1,050,000-token context window (vendor spec) with 128K max output tokens, supports image input, configurable reasoning effort from none to xhigh, discounted cached input, and the full hosted tool set including web search and code interpreter, with an August 2025 knowledge cutoff.
  • It is the default choice when flagship capability must meet production economics.
  • Synthorai customers reach GPT-5.4 through the gateway's OpenAI-compatible chat completions endpoint.

Specs & limits

Max output (vendor spec)128,000
Modalitiestext + image → text
Featurestools · parallel_tool_calls · structured_output · streaming · vision · batch · reasoning · realtime · computer_use · caching
Notable1.05M-token context / 128k max output; prompts over 272k input tokens billed at 2x input / 1.5x output; reasoning effort none-xhigh.
Prompt cachingautomatic · min 1,024-token prefix · TTL 5–10m, up to 1h

per OpenAI official docs ↗

FAQ

Is the GPT-5.4 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $2.5/M input tokens, that credit alone covers roughly 49 requests of ~8K tokens against GPT-5.4.

What is GPT-5.4 best at?

1,050,000-token context window, plus more affordable flagship-class option and full hosted tool set including web search. See the About section for the full picture from the vendor's own release notes.

How much does GPT-5.4 cost?

GPT-5.4 costs $2.5 per million input tokens and $15 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $1.25/M.

Does GPT-5.4 support prompt caching?

Yes, automatically: OpenAI-served prompts cache with no code changes. Cached input tokens bill at $1.25/M vs $2.5/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?

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

What is GPT-5.4's knowledge cutoff?

GPT-5.4's knowledge cutoff is 2025-08, per the vendor's official documentation (as of 2026-07-09).

Related models

Get your free API key Compare your cost →