How much does GPT-5.4 Image 2 cost?

$8 per million input tokens and $15 per million output tokens at list price, with cached input at $2. The cheapest route is $8 in and $15 out. Hoodgen bills in credits (1 credit = Rs 0.10) and shows the estimate before you send.

What is the context window of GPT-5.4 Image 2?

272,000 input tokens with up to 128,000 output tokens.

Is GPT-5.4 Image 2 good for coding?

It is built for multi step work: read a failure, form a hypothesis, patch, re-run.

Does GPT-5.4 Image 2 accept images, audio or files?

It accepts image, text, file and returns image, text. Drop an image into the Hoodgen composer and ask about it directly.

How fast is GPT-5.4 Image 2?

Artificial Analysis does not publish latency for this release.

What is the Artificial Analysis score of GPT-5.4 Image 2?

Artificial Analysis does not publish an Intelligence Index for this release, so no score is claimed.

How do I use GPT-5.4 Image 2 on Hoodgen?

Open Chat, pick GPT-5.4 Image 2 in the model menu and send a prompt. No API key, no card, paid in credits. It is also selectable inside Coding, Writer and the other tools.

OpenAIReasoningReleased 21 April 2026

GPT-5.4 Image 2 pricing, context and benchmark

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2.

Chat with GPT-5.4 Image 2 Create image with GPT-5.4 Image 2

272K

Input context

128K

Output context

Official input

$15

Official output

n/a

AA index

01 · Model Overview

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

Model	GPT-5.4 Image 2
Model ID	openai/gpt-5.4-image-2
Provider	OpenAI
Release date	21 April 2026
Status	Generally available
Input context	272,000 tokens
Output context	128,000 tokens
Official input pricing	$8 per 1M tokens
Official output pricing	$15 per 1M tokens
Cache read pricing	$2 per 1M tokens
Market input pricing	$8 per 1M (cheapest route)
Market output pricing	$15 per 1M (cheapest route)
Reasoning tokens	Billed as output at $15 per 1M
Input modalities	image · text · file
Output modalities	image · text
Reasoning control	Yes, effort levels exposed
Tool support	Text generation only
Tokenizer	GPT
Provider routes	1 endpoint
Artificial Analysis index	Not published
Speed	Not published
Knowledge cutoff	Not publicly stated

Input and output support

Modality	Input	Output	Billed at
Text	✓ yes	✓ yes	$8 in
Image	✓ yes	✓ yes	$8 in
Audio	no	no	not supported
Video	no	no	not supported
File (PDF)	✓ yes	no	$8 in

02 · Overview

What is GPT-5.4 Image 2?

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2.

It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

GPT-5.4 Image 2 carries a 272K token window, uses the GPT tokenizer and is served by OpenAI. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

03 · Release

Release and what changed from the previous version

Released21 April 2026

Property	GPT-5.4 Mini	GPT-5.4 Image 2	Change
Released	2026	2026	Same release window
Context	400K	272K	Changed
Max output	128K	128K	Unchanged
Input price	$0.75	$8	Higher
Output price	$4.5	$15	Higher
Input modalities	file, image, text	image, text, file	Unchanged
AA index	n/a	n/a	Newer benchmark run

04 · Capabilities

Features and capabilities

◈

Thinking control

Reasoning effort can be dialled per request, so one model covers deep analysis and fast chat.

{ }

Structured outputs

Schema constrained JSON with response_format, so no parse and retry loop in your code.

◉

Vision

Screenshots, charts and photographed documents are read at the text token rate.

▤

Files and PDFs

Documents go in as files rather than pasted text, keeping layout and tables intact.

⚡

Prompt caching

Cached input costs $2 per million instead of $8, so stable prefixes get cheaper.

⌁

Seeds

A seed can be pinned so the same prompt is reproducible across test runs.

05 · Reasoning

Thinking and reasoning capabilities

GPT-5.4 Image 2 can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $15 per million, and the trace can be returned with include_reasoning.

Level	First token	Cost per task	Best for
Measured	n/a	n/a	Artificial Analysis measures the default reasoning configuration
Low effort	Faster	Lower	Chat, autocomplete, classification
High effort	Slower	Higher	Debugging, planning, multi step agents

07 · Use cases

What can you do with GPT-5.4 Image 2?

Debugging and root cause

Multi file failures where the model has to hold a causal chain before answering.

Architecture and planning

Design docs, migration plans and trade off analysis over long context.

Data analysis

Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.

Agentic coding

Repo wide changes that need plan, edit and verify loops.

08 · Cost levers

Prompt caching and how to cut the bill

Cached input bills at $2 per million instead of $8. Keep the system prompt and documents first and the changing question last, so every call hits the cache.

09 · Pricing

GPT-5.4 Image 2 pricing

Official pricing

List price

$8 / 1M in

$15 / 1M out

$2 cached input
272K context
image, text, file input

Cheapest route

$8 / 1M in

$15 / 1M out

1 route on OpenRouter
What Hoodgen routes to first
Same model, lower bill

Market pricing, every route

Provider	Tier	Input	Output	Cache read	Uptime 24h
OpenAI	standard	$8	$15	$2	100.0%

API pricing and cost calculator

Input tokens per callOutput tokens per callCache hit %Number of calls

Rate	Per call	Total	Credits
Cheapest route	$0.1105	$55.25	52488
List price	$0.1105	$55.25	52488

10 · Developers

API and developer information

Model ID	openai/gpt-5.4-image-2
Endpoint	https://openrouter.ai/api/v1/chat/completions
Parameters	include_reasoning · logprobs · max_tokens · reasoning · reasoning_effort · response_format · seed · structured_outputs · top_logprobs · verbosity
Streaming	Yes, server sent events
Modality string	text+image+file->text+image
Max prompt tokens	272,000
Max completion tokens	128,000

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-image-2",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'

11 · Limitations

Model limitations

Output cap	128,000 tokens per request. Long deliverables have to be chunked.
Benchmarks not published	Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoff	The provider does not state a fixed cutoff for every release. Verify very recent events against search.

12 · Comparison

GPT-5.4 Image 2 vs other OpenAI models

Model	Context	Input /1M	Output /1M	AA index	Released
GPT-5.4 Image 2	272K	$8	$15	n/a	2026
GPT-5.5 Pro	1.05M	$30	$180	n/a	2026
GPT-5.4 Pro	1.05M	$30	$180	n/a	2026
GPT-5.2 Pro	400K	$21	$168	n/a	2025
o3 Pro	200K	$20	$80	n/a	2025
GPT-5 Pro	400K	$15	$120	n/a	2025

13 · Privacy

Privacy and data policy

On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
Requests route through OpenRouter to OpenAI and are covered by that provider's API terms.
Do not paste secrets or personal data you would not send to any hosted model.

14 · FAQ

GPT-5.4 Image 2 questions, answered

GPT-5.4 Image 2 is a reasoning model from OpenAI, released 21 April 2026. [GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2.

✦

Start chatting with GPT-5.4 Image 2

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.

Open Chat, it is free Compare all models