Back to model shop
Openai
Rendered from D1 model snapshot · D1 read 96msCache check: checking

openai/gpt-5.4-pro

GPT-5.4 Pro

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

This model's cache

This model page returns the exact headers below. The page and /api/models/openai--gpt-5.4-pro share the model:openai--gpt-5.4-pro tag, so invalidation stays scoped to this model.

Cache key/models/openai--gpt-5.4-pro
Cache-Controlpublic, max-age=300, stale-while-revalidate=3600
Cache-Tagcatalogmodel:openai--gpt-5.4-pro

Workers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.

export const Route = createFileRoute('/models/$modelSlug')({
  headers: () => ({
    'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
    'Cache-Tag': 'catalog,model:openai--gpt-5.4-pro',
  }),
})

Invalidate this cache tag

await ctx.cache.purge({ tags: ['model:openai--gpt-5.4-pro'] })

Use this when one model changes and you do not want to evict the whole catalog.

Gpt ProReasoningTool callingAttachments
Released
Mar 5, 2026
Last updated
Mar 5, 2026
Context window
1.1M tokens
Max output
128K tokens
Open weights
No
Family
Gpt Pro

Starts at

$27

per 1M input tokens

Output

$160

Sellers

9

No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.

Capabilities & modalities
Reasoning
Tool calling
Structured output
Attachments
InputText, Image
OutputText
Provider shelf
Where to get GPT-5.4 Pro

Sorted by lowest input price

ProviderInput / 1MOutput / 1MContext

Poe

openai/gpt-5.4-pro

$27$1601.1MDocs

Requesty

openai/gpt-5.4-pro

$30$1801.1MDocs

Vercel AI Gateway

openai/gpt-5.4-pro

$30$1801.1MDocs

OpenAI

gpt-5.4-pro

$30$1801.1MDocs

Kilo Gateway

openai/gpt-5.4-pro

$30$1801.1MDocs

OpenRouter

openai/gpt-5.4-pro

$30$1801.1MDocs

NanoGPT

openai/gpt-5.4-pro

$30$180922KDocs

ZenMux

openai/gpt-5.4-pro

$45$2251.1MDocs

OrcaRouter

openai/gpt-5.4-pro

$60$2701.1MDocs
More from Openai