OpenaiFastReleased 17 March 2026
GPT-5.4 Nano pricing, context and benchmark
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.
400K
Input context
128K
Output context
$0.2
Official input
$1.25
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 Nano |
| Model ID | openai/gpt-5.4-nano |
| Provider | Openai |
| Release date | 17 March 2026 |
| Status | Generally available |
| Input context | 400,000 tokens |
| Output context | 128,000 tokens |
| Official input pricing | $0.2 per 1M tokens |
| Official output pricing | $1.25 per 1M tokens |
| Cache read pricing | $0.02 per 1M tokens (90% off input) |
| Market input pricing | $0.1 per 1M (cheapest route) |
| Market output pricing | $0.625 per 1M (cheapest route) |
| Highest route pricing | $0.22 in, $1.375 out per 1M |
| Input modalities | file · image · text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | GPT |
| Provider routes | 4 endpoints |
| Artificial Analysis index | Not published |
| Speed | 149 tokens/s, 62.38s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.2 in |
| Image | ✓ yes | no | $0.2 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | ✓ yes | no | $0.2 in |
02 · Overview
What is GPT-5.4 Nano?
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.
It supports text and image inputs and is designed for low-latency...
GPT-5.4 Nano carries a 400K token window, uses the GPT tokenizer and is served by Openai. On Hoodgen it sits in the Fast 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
Released17 March 2026
| Property | GPT-5.2-Codex | GPT-5.4 Nano | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 400K | 400K | Unchanged |
| Max output | 128K | 128K | Unchanged |
| Input price | $1.75 | $0.2 | Cheaper |
| Output price | $14 | $1.25 | Cheaper |
| Input modalities | text, image | file, image, text | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
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 $0.02 per million instead of $0.2, so stable prefixes get cheaper.
07 · Use cases
What can you do with GPT-5.4 Nano?
High volume drafts
Captions, titles, product blurbs and rewrite passes where cost per call dominates.
Inline assistants
Autocomplete, quick replies and menu helpers that must answer inside a second.
Batch classification
Tagging, routing and extraction across thousands of short inputs.
Cheap agent loops
Tool calling loops that do not need frontier grade reasoning.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.02 per million instead of $0.2, a 90% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
GPT-5.4 Nano pricing
Official pricing
List price
$0.2 / 1M in
$1.25 / 1M out
- $0.02 cached input
- 400K context
- file, image, text input
Cheapest route
$0.1 / 1M in
$0.625 / 1M out
- 4 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$0.22 / 1M in
$1.375 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| OpenAI | flex | $0.1 | $0.625 | $0.01 | 100.0% |
| Azure | standard | $0.2 | $1.25 | $0.02 | 100.0% |
| OpenAI | standard | $0.2 | $1.25 | $0.02 | 97.7% |
| Azure | standard | $0.22 | $1.375 | $0.022 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0019 | $0.93 | 883 |
| List price | $0.0037 | $1.86 | 1765 |
| Highest route | $0.0065 | $3.23 | 3070 |
10 · Developers
API and developer information
| Model ID | openai/gpt-5.4-nano |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+file->text |
| Max prompt tokens | 400,000 |
| 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-nano",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| 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. |
| Depth ceiling | Fast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning. |
12 · Comparison
GPT-5.4 Nano vs other Openai models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| GPT-5.4 Nano | 400K | $0.2 | $1.25 | n/a | 2026 |
| GPT-6 Astra | 1.05M | $10 | $50 | 57 | Sep 2026 |
| GPT-6 Astra Pro | 1.05M | $10 | $50 | n/a | Sep 2026 |
| GPT-5.6 Sol | 1.05M | $4 | $20 | n/a | 2026 |
| GPT-5.6 Sol Pro | 1.05M | $4 | $20 | n/a | 2026 |
| GPT-5.6 Terra | 1.05M | $2 | $12 | 32 | 2026 |
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 Nano questions, answered
GPT-5.4 Nano is a fast model from Openai, released 17 March 2026. GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.
✦
Start chatting with GPT-5.4 Nano
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.